# LLM Agent Reasoning and Planning > Search results for `planning and reasoning loops for LLM agents` on awesome-repositories.com. 116 total matches; showing the first 50. Explore on the web: https://awesome-repositories.com/q/planning-and-reasoning-loops-for-llm-agents **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [this search on awesome-repositories.com](https://awesome-repositories.com/q/planning-and-reasoning-loops-for-llm-agents).** ## Results - [camel-ai/camel](https://awesome-repositories.com/repository/camel-ai-camel.md) (17,253 ⭐) — This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-evaluate reasoning traces, ensuring high-quality results. To maintain operational integrity, the system enforces schema-based output parsing for reliable workflow integration and utilizes sandboxed environments for secure, isolated code execution. Beyond its core orchestration capabilities, the project includes a suite of utilities for retrieval-augmented generation and synthetic data production. It supports persistent memory management via vector-based context retrieval and provides extensive tooling for web automation, API integration, and human-in-the-loop oversight. The platform is designed to be model-agnostic, offering a consistent interface for interacting with a wide range of proprietary and open-source language models. - [agentscope-ai/agentscope](https://awesome-repositories.com/repository/agentscope-ai-agentscope.md) (26,895 ⭐) — Agentscope is a comprehensive toolkit for developing and orchestrating autonomous multi-agent systems. It provides a unified framework for building agents that can reason, execute tools, and manage memory, enabling the creation of complex, collaborative workflows where multiple specialized agents interact to solve multi-step objectives. The platform distinguishes itself through a robust orchestration engine that supports both sequential and concurrent agent pipelines. It utilizes a centralized event bus for real-time telemetry, allowing developers to track agent reasoning, tool usage, and system performance. By employing a provider-agnostic interface, the framework abstracts diverse language model APIs, while its middleware-based execution hooks allow for the injection of custom logic to intercept, validate, or transform agent behavior at runtime. Beyond core orchestration, the project includes extensive capabilities for tool integration, including dynamic schema parsing from function docstrings and support for secure, sandboxed code execution. It also features built-in support for retrieval-augmented generation, long-term memory management, and systematic performance evaluation, providing a complete environment for the lifecycle management of agentic applications. The library is designed for extensibility, offering base classes for custom memory backends, prompt formats, and tool providers. It is distributed as a Python package, with documentation and interactive development tools available to assist in prototyping and managing multi-agent projects. - [datawhalechina/hello-agents](https://awesome-repositories.com/repository/datawhalechina-hello-agents.md) (59,685 ⭐) — This project provides a comprehensive framework for building, training, and managing autonomous agents. It enables the construction of systems that utilize language models to plan, manage memory, and execute multi-step tasks through iterative reasoning loops and tool-based actions. The framework distinguishes itself by offering specialized capabilities for interacting with graphical user interfaces and legacy software, allowing agents to perceive visual elements and perform actions like a human user. It supports complex, cross-application workflows through graph-based orchestration and provides robust mechanisms for skill evolution, where agents can iteratively refine or generate new operational capabilities based on execution feedback. Beyond core development, the project includes an extensive suite of tools for model training and optimization, including multi-stage fine-tuning, reinforcement learning, and multimodal alignment. It also features integrated observability tools for monitoring agent execution, managing persistent context, and ensuring security through sandboxed environments and risk-aware execution controls. The repository serves as both a functional development framework and an educational resource, offering structured guides and methodologies for implementing intelligent agent systems. - [mastra-ai/mastra](https://awesome-repositories.com/repository/mastra-ai-mastra.md) (21,221 ⭐) — Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execution. It features a built-in telemetry pipeline that captures structured execution traces, logs, and performance metrics, allowing for real-time debugging and evaluation of agent behavior. Furthermore, it utilizes sandboxed environments to isolate code execution and filesystem operations, ensuring that agent interactions remain secure and reproducible. Mastra covers a broad capability surface, including multi-agent delegation hierarchies, schema-validated tool execution, and real-time voice interaction. It supports advanced orchestration patterns such as human-in-the-loop approvals, persistent state management for long-running workflows, and retrieval-augmented generation using vector-based semantic memory. These features are designed to work together to support the entire lifecycle of AI-powered applications, from initial development and testing to production deployment. The project is built for TypeScript environments and provides a modular architecture that integrates with existing web stacks and infrastructure. It includes a client SDK for interacting with remote agents and supports various authentication providers to secure API endpoints and agent resources. - [datawhalechina/tiny-universe](https://awesome-repositories.com/repository/datawhalechina-tiny-universe.md) (4,505 ⭐) — Tiny Universe is an educational monorepo that delivers multiple independent implementations of core AI subsystems as self-contained Jupyter notebooks. It provides from-scratch constructions of foundational architectures including a complete Transformer model built from the original paper specification, a denoising diffusion probabilistic model for image generation, and a ReAct-style autonomous agent framework that equips an LLM with tools for planning and multi-step task execution. The project distinguishes itself by covering the full lifecycle of modern AI systems through hands-on implementations. It includes retrieval-augmented generation pipelines that combine vector databases with knowledge graphs, a GraphRAG system that constructs knowledge graphs from text and generates hierarchical community summaries, and a two-stage evaluation pipeline that scores model outputs against reference answers using metrics like F1, ROUGE, and accuracy. The repository also demonstrates reinforcement learning fine-tuning, automated document review workflows that detect deviations and generate revision suggestions, and iterative image optimization that evaluates and improves generated images against text prompts. Beyond these core areas, Tiny Universe explores the internal mechanisms of large language models with walkthroughs of grouped query attention, rotary position embeddings, and causal masking. It covers data processing techniques such as semantic chunking by sentence shifts, vector embedding pipelines for similarity-based retrieval, and hybrid search strategies that fuse sentence-level similarity with domain-specific term importance. The project also includes image quality evaluation using Inception Score and Fréchet Inception Distance, as well as image-text consistency checking with vision-language models. All implementations are delivered as self-contained Jupyter notebooks within a single repository, making the code directly runnable and inspectable for educational purposes. - [dair-ai/prompt-engineering-guide](https://awesome-repositories.com/repository/dair-ai-prompt-engineering-guide.md) (75,678 ⭐) — This project is a comprehensive educational resource and technical guide focused on the development, optimization, and application of large language models. It provides a structured curriculum for mastering prompt engineering, ranging from foundational principles of instruction design to advanced techniques for improving model reasoning, accuracy, and reliability. The guide distinguishes itself by offering deep technical insights into agentic workflows and autonomous system design. It covers the implementation of multi-step reasoning chains, tool integration through function calling, and stateful memory management. Beyond basic prompting, it explores sophisticated frameworks that combine reasoning and acting, as well as methodologies for retrieval-augmented generation and the creation of synthetic datasets to address data scarcity in specialized domains. The documentation also addresses the broader engineering surface of AI development, including defensive strategies for application security and automated evaluation loops for model verification. These resources are designed to support developers in building complex, task-oriented AI systems that can interact with external APIs and maintain continuity across long-running processes. - [maitrix-org/llm-reasoners](https://awesome-repositories.com/repository/maitrix-org-llm-reasoners.md) (0 ⭐) — LLM Reasoners is a library to enable LLMs to conduct complex reasoning, with advanced reasoning algorithms. It approaches multi-step reasoning as planning and searches for the optimal reasoning chain, which achieves the best balance of exploration vs exploitation with the idea of "World Model"… - [eosphoros-ai/db-gpt](https://awesome-repositories.com/repository/eosphoros-ai-db-gpt.md) (18,999 ⭐) — DB-GPT is an agentic data analysis platform and business intelligence AI that functions as a large language model data assistant. It provides a text-to-SQL interface and a sandboxed code execution environment to translate natural language into executable database queries and Python scripts. The platform utilizes iterative agentic reasoning to plan and execute multi-step data analysis workflows through tool calls. It features a modular skill-based extension system that allows domain knowledge and analysis workflows to be packaged into reusable functional components. The system integrates data from relational databases, spreadsheets, and unstructured documents to automate the generation of analytical reports, financial summaries, and visual dashboards. Security is managed by running generated code and analytical tools within isolated sandbox environments. - [conductor-oss/conductor](https://awesome-repositories.com/repository/conductor-oss-conductor.md) (31,962 ⭐) — Conductor is a durable workflow engine designed to orchestrate complex, long-running business processes and autonomous agent loops. It functions as a stateful execution platform that persists the entire history of a process, ensuring that workflows remain reliable and recoverable across infrastructure failures, system restarts, and transient network errors. By managing task lifecycles, worker polling, and state transitions, it provides a centralized coordination layer for distributed systems. The platform distinguishes itself through its specialized support for AI agent orchestration, allowing developers to build autonomous loops that plan, act, and observe using model-based reasoning. It integrates AI capabilities directly into durable pipelines, enabling features like automated tool discovery, token usage optimization, and human-in-the-loop approval gates. These agentic workflows can be composed of nested sub-agents and dynamic execution paths, all while maintaining full auditability and state persistence for every model call and tool interaction. Beyond its agentic capabilities, the engine provides a comprehensive suite of tools for managing distributed tasks, including event-driven triggers, complex compensation logic, and polyglot worker support. It allows for the construction of dynamic task graphs that adapt at runtime, ensuring that business logic remains flexible and scalable. The system supports horizontal scaling through a queue-based distribution model, enabling teams to coordinate microservices and external systems within a single, observable execution environment. - [harishsg993010/llm-reasoner](https://awesome-repositories.com/repository/harishsg993010-llm-reasoner.md) (0 ⭐) — Make any LLM to think deeper like OpenAI o1 and deepseek R1! - [agno-agi/agno](https://awesome-repositories.com/repository/agno-agi-agno.md) (40,717 ⭐) — Agno is an agent operating system designed to manage the lifecycle, tool execution, and persistent state of autonomous agents across distributed infrastructure. It provides a unified runtime environment that wraps diverse agent frameworks into a consistent, interoperable protocol, allowing developers to build and deploy complex multi-agent systems that coordinate tasks and delegate sub-processes. The platform distinguishes itself through a robust governance and orchestration layer that includes human-in-the-loop approval gates, role-based access control, and a centralized API gateway. It features a shared cultural knowledge layer that enables agents to reflect on interactions and store universal principles across sessions, alongside persistent memory architectures that manage chat history and context retrieval. The system supports a wide range of operational capabilities, including real-time response streaming, asynchronous background task management, and automated performance evaluation. It integrates with external systems through standardized interfaces and provides comprehensive observability tools to trace autonomous decision paths and monitor agent accuracy in production environments. Developers can configure the system using typed classes or YAML files, and the platform exposes agents as secure, scalable web services with built-in middleware for authentication and request validation. - [dontriskit/awesome-ai-system-prompts](https://awesome-repositories.com/repository/dontriskit-awesome-ai-system-prompts.md) (5,206 ⭐) — This project is a comprehensive library of structured system prompts and configuration templates designed to define the behavior, persona, and operational boundaries of autonomous artificial intelligence agents. It serves as a framework for prompt engineering, providing modular instructions that help models parse complex tasks, maintain consistent interaction tones, and adhere to specific domain constraints. The repository distinguishes itself by offering specialized configurations for agent safety and security, including protocols to prevent prompt injection and unauthorized data access. It provides standardized schemas for tool integration, enabling agents to interact reliably with external APIs, web interfaces, and local system environments. By utilizing these modular components, users can establish clear scopes for agent autonomy and enforce methodical reasoning loops that improve task accuracy. Beyond core configuration, the project covers a broad range of capabilities for managing autonomous workflows, including file system operations, code execution, and real-time information retrieval. It supports the development of persistent, context-aware agents capable of tracking multi-step progress and summarizing interaction history. The documentation and templates are organized to facilitate the rapid deployment of agents across various research, coding, and data analysis environments. - [agi-edgerunners/plan-and-solve-prompting](https://awesome-repositories.com/repository/agi-edgerunners-plan-and-solve-prompting.md) (0 ⭐) — Code for our ACL 2023 Paper "Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models". - [j3ssie/osmedeus](https://awesome-repositories.com/repository/j3ssie-osmedeus.md) (6,425 ⭐) — Osmedeus is an LLM security orchestration engine and AI agent framework designed to automate security workflows. It functions as a declarative workflow automator that uses YAML definitions to coordinate AI agents, shell commands, and distributed scanning tools through a directed acyclic graph. The system distinguishes itself by deploying autonomous AI agents that use tool-calling loops and conversation memory to plan and execute complex analysis tasks. It features a specialized Agent Communication Protocol to delegate tasks to external AI binaries and supports recursive sub-agent orchestration for delegated task handling. The platform covers a broad range of capabilities, including distributed security scanning across cloud infrastructure and the management of large-scale attack surface discovery. It incorporates a hybrid runner model to execute tasks across local shells, Docker containers, and remote SSH hosts, while persisting artifacts in S3-compatible storage and tracking findings in a centralized database. The engine can be embedded as a Go library or managed via a REST API and web interface. - [virattt/dexter](https://awesome-repositories.com/repository/virattt-dexter.md) (27,085 ⭐) — Dexter is an autonomous research platform designed to decompose complex inquiries into structured, multi-step workflows. It functions as an agent orchestration system that utilizes iterative tool-calling loops and language models to gather data, perform analysis, and validate findings against internal criteria to ensure accuracy. The platform distinguishes itself through its specialized focus on financial research and messaging integration. It autonomously interprets real-time market data, including income statements and regulatory filings, to generate evidence-based insights. By connecting directly to chat platforms, the system allows users to submit queries and receive detailed analytical reports within group conversations, while maintaining secure access policies and account management. The architecture supports a model-agnostic interface, allowing for the selection of various language model providers to balance performance and cost. It includes comprehensive observability tools that record reasoning processes, tool interactions, and execution history, providing transparency into how the agent reaches its conclusions. - [rlhflow/self-rewarding-reasoning-llm](https://awesome-repositories.com/repository/rlhflow-self-rewarding-reasoning-llm.md) (0 ⭐) — TL;DL: this is the repo for " Self-rewarding Correction for Mathematical Reasoning " - [oxbshw/llm-agents-ecosystem-handbook](https://awesome-repositories.com/repository/oxbshw-llm-agents-ecosystem-handbook.md) (0 ⭐) — A practical operating manual for building, evaluating, securing, and shipping modern LLM agent systems. - [vercel/ai](https://awesome-repositories.com/repository/vercel-ai.md) (21,885 ⭐) — This project is a comprehensive framework for building AI-powered applications, providing a unified toolkit for orchestrating language models, autonomous agents, and interactive user interfaces. It serves as a central library for managing the entire lifecycle of AI interactions, from initial prompt generation and model provider abstraction to complex, multi-step reasoning and tool execution. The framework distinguishes itself through its deep integration with frontend development, specifically by enabling generative user interfaces that render dynamic components directly from model outputs. It features a robust agentic execution engine that manages recursive reasoning loops, allowing developers to define custom stopping conditions, delegate tasks to subagents, and enforce structured workflows. By providing a standardized interface for streaming data and state management, it ensures that backend model responses and frontend UI components remain synchronized in real time. Beyond its core orchestration capabilities, the project covers a broad surface of AI integration features, including schema-driven data extraction, multi-modal input processing, and middleware-based request interception. It supports a wide range of operational needs such as persistent conversation history, retrieval-augmented generation, and comprehensive observability tools for monitoring token usage and execution flows. The library is designed for TypeScript environments and provides a collection of hooks and utilities that simplify the implementation of chat interfaces and agentic workflows. - [atfortes/awesome-llm-reasoning](https://awesome-repositories.com/repository/atfortes-awesome-llm-reasoning.md) (3,640 ⭐) — From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓 - [tmc/langchaingo](https://awesome-repositories.com/repository/tmc-langchaingo.md) (9,416 ⭐) — langchaingo is an LLM application framework for Go designed for building language model-powered applications and autonomous agents. It serves as an orchestration library and tool integration framework that allows developers to link prompt sequences and model calls into complex, multi-step workflows. The project provides a toolkit for implementing retrieval-augmented generation pipelines by processing unstructured documents and retrieving relevant context via vector search. It includes a dedicated integration layer for indexing high-dimensional embeddings and performing similarity searches across various vector database backends. Its broader capabilities cover AI workflow automation, the creation of autonomous agents that use reasoning to execute external tools, and the management of conversation state to maintain context across multi-turn dialogues. The framework also supports integrating external search tools, executing database queries, and triggering third-party workflows. - [flowiseai/flowise](https://awesome-repositories.com/repository/flowiseai-flowise.md) (53,641 ⭐) — Flowise is a low-code platform designed for building and deploying complex language model workflows through a visual, node-based interface. It functions as an orchestrator for autonomous multi-agent systems, allowing users to construct conversational pipelines by connecting language models, memory stores, and external tools on a drag-and-drop canvas. The platform distinguishes itself through its support for sophisticated agentic patterns, including supervisor-worker delegation and iterative reasoning strategies. Users can design directed acyclic graphs to manage conditional branching, state persistence, and complex task distribution. It also provides a robust framework for retrieval-augmented generation, enabling the creation of self-correcting systems that can index document data and validate information autonomously. Beyond its visual design capabilities, the project serves as a comprehensive backend for AI applications. It includes a secure credential management layer for third-party API keys, role-based access controls, and a RESTful API that allows for programmatic management of chat sessions, workflows, and assistant configurations. The application is designed for flexible deployment, supporting containerized environments for consistent operation across local and cloud infrastructure. Detailed documentation and tutorials are available to guide users through the lifecycle of building, testing, and scaling production-ready AI agents. - [crewaiinc/crewai](https://awesome-repositories.com/repository/crewaiinc-crewai.md) (53,687 ⭐) — CrewAI is a multi-agent orchestration framework designed for building autonomous systems that execute complex, multi-step workflows. It provides a development platform where specialized agents are defined with specific roles, goals, and tool sets to perform tasks collaboratively. By leveraging a declarative workflow engine, the system manages task dependencies, state transitions, and execution logic, allowing for the creation of structured, stateful sequences of operations. The framework distinguishes itself through its hierarchical management capabilities, which utilize manager agents to coordinate specialist teams, delegate tasks, and oversee project execution. It incorporates a persistent memory architecture that enables agents to retain context and perform semantic searches across long-running operations. Furthermore, the system supports robust production-ready applications by enforcing schema-based output validation and providing execution checkpointing, which allows for mid-flight resumption and the replaying of specific tasks to debug or refine processes. Beyond its core orchestration, the project offers a comprehensive suite of developer utilities for managing agent performance and workflow reliability. This includes tools for training agents through iterative cycles, monitoring system events via a central execution bus, and visualizing workflow structures. The platform also features a provider-agnostic interface for integrating external APIs and utilities, ensuring that agents can interact with diverse real-world services while maintaining consistent data structures throughout the execution lifecycle. - [tencentcloudadp/youtu-agent](https://awesome-repositories.com/repository/tencentcloudadp-youtu-agent.md) (4,576 ⭐) — Youtu Agent is an open-source framework for building, running, and evaluating autonomous agents powered by large language models. It provides the core infrastructure for creating agents that follow reasoning loops, use toolkits, and coordinate with other agents to solve complex tasks, all managed through YAML-driven configuration files. The framework distinguishes itself through its support for multi-agent orchestration, where a planner agent decomposes tasks and coordinates specialized worker agents, and through its integration with the Model Context Protocol for connecting to external toolkits. It includes a sandboxed code execution environment that supports over 20 programming languages, browser automation capabilities for web research, and a trajectory-based performance distillation method that improves agent performance without fine-tuning model parameters. Beyond core agent development, the framework offers a comprehensive evaluation pipeline with database-backed experiment tracking, configurable judging using language models or rule-based matching, and support for resuming interrupted evaluations. It provides tooling for defining custom reward functions, running multi-phase benchmarks, and comparing experiment results. The system also includes web-based interfaces for interacting with agents, Docker deployment options, and support for multimodal inputs including images and video. - [briland/llm-security-and-privacy](https://awesome-repositories.com/repository/briland-llm-security-and-privacy.md) (54 ⭐) — LLM security and privacy - [tencent/weknora](https://awesome-repositories.com/repository/tencent-weknora.md) (16,974 ⭐) — WeKnora is a multi-tenant retrieval-augmented generation (RAG) knowledge platform and autonomous AI agent framework. It transforms raw documents into queryable knowledge bases and integrates large language models with vector databases to provide grounded AI responses. The system also functions as a Model Context Protocol (MCP) tool server, exposing knowledge search and agentic capabilities to external AI clients. The platform distinguishes itself through an autonomous agent framework that utilizes iterative reasoning, tool calling, and web search to solve multi-step tasks. It implements a standardized tool surface via the Model Context Protocol, allowing for the extension of agent capabilities through custom skill definitions and external service integration. The system covers comprehensive data management areas, including recursive document chunking, hybrid search retrieval with cross-encoder reranking, and complex document parsing via OCR. It provides enterprise-grade infrastructure with multi-tenant data isolation, role-based access control, and OIDC authentication. Additional capabilities include the generation of structured wikis and knowledge graphs from ingested content, as well as integration with third-party messaging platforms. The project can be deployed via Kubernetes or as a standalone lite distribution. - [miserlou/loop](https://awesome-repositories.com/repository/miserlou-loop.md) (696 ⭐) — UNIX's missing `loop` command - [huggingface/smolagents](https://awesome-repositories.com/repository/huggingface-smolagents.md) (27,885 ⭐) — This framework provides a development toolkit for building autonomous agents that utilize language models to solve complex, non-deterministic tasks. Its core design centers on a code-executing architecture where agents generate and run Python code snippets to perform logic, data manipulation, and tool interactions. By moving beyond structured data formats, the system enables agents to manage program flow and object state through iterative reasoning cycles. The project distinguishes itself through its focus on code-based agent implementation and secure execution environments. Developers can choose between code-generating agents for complex logic or structured tool-calling agents for reliable, schema-validated interactions. To ensure safety when running model-generated scripts, the framework supports isolated runtime environments, including containers and remote virtual machines, which prevent unauthorized system access while maintaining state across task cycles. The platform offers a comprehensive suite of capabilities for managing agentic workflows, including multi-agent orchestration, stateful memory management, and interactive planning. It provides a unified interface for integrating diverse language model providers and simplifies tool creation by automatically converting Python functions into executable tools via metadata and type hints. Users can monitor the decision-making process through an interactive interface that visualizes reasoning steps and supports manual intervention during task execution. - [micro/go-micro](https://awesome-repositories.com/repository/micro-go-micro.md) (22,810 ⭐) — Go-micro is a distributed systems development toolkit designed for building, connecting, and managing modular microservices. It provides a comprehensive framework for service discovery, remote procedure call abstraction, and event-driven messaging, allowing developers to create decoupled architectures that communicate asynchronously through shared message brokers. The project distinguishes itself by integrating autonomous agent orchestration and language model tool binding directly into the service lifecycle. By exposing internal service endpoints as standardized tools, it enables AI agents to discover and execute functions, manage multi-step workflows, and maintain persistent state. This architecture is supported by a pluggable interface system that allows developers to swap infrastructure components like storage backends or service registries without modifying core application logic. Beyond its core communication and orchestration capabilities, the framework includes a robust suite of tools for service management, including an HTTP gateway for protocol translation, granular access control, and distributed observability. It also provides a command-line interface for project scaffolding, hot-reloading, and automated code generation, alongside a web-based dashboard for monitoring service health and inspecting endpoint schemas. - [microsoft/ai-agents-for-beginners](https://awesome-repositories.com/repository/microsoft-ai-agents-for-beginners.md) (67,369 ⭐) — This project is a structured educational resource and technical guide for designing and implementing autonomous systems using large language models. It provides a comprehensive curriculum and code samples focused on agentic design patterns, autonomous development, and the creation of systems capable of planning and executing multi-step tasks. The resource details the implementation of agentic retrieval-augmented generation, where models autonomously plan and refine data searches. It covers a wide array of orchestrators and design patterns, including metacognitive reflection for self-correcting reasoning and human-in-the-loop oversight for critical action approval. The materials extend to the coordination of multi-agent systems through task decomposition and communication protocols, as well as the management of short-term session context and long-term persistent memory. Further technical coverage includes agent observability, secure deployment practices, and the integration of external tools and data sources. The project is delivered primarily as a collection of Jupyter Notebooks. - [swe-agent/mini-swe-agent](https://awesome-repositories.com/repository/swe-agent-mini-swe-agent.md) (2,947 ⭐) — mini-swe-agent is an autonomous software engineering system designed to develop features and fix bugs by combining large language models with a bash interface. It operates as an agentic framework that executes coding tasks and documentation updates through a continuous cycle of model reasoning and tool execution. The project differentiates itself with a strong focus on safety and evaluation, utilizing container-based sandbox execution via Docker or Singularity to isolate command execution. It includes a batch-parallel evaluation harness to measure code-fixing accuracy against standardized software engineering datasets and a constraint-based control system to enforce limits on step counts, time, and API expenditure. The system provides comprehensive LLM API orchestration, supporting a unified interface for multiple model providers, native tool calling, and detailed expenditure tracking. Additional capabilities cover interactive human-in-the-loop oversight via a REPL-style interface, trajectory serialization for post-run analysis, and a flexible configuration system using Jinja2 templates for prompt and observation formatting. - [truhnlab/contrastive-agent-reasoning](https://awesome-repositories.com/repository/truhnlab-contrastive-agent-reasoning.md) (0 ⭐) — by Zihao Zhao, Frederik Hauke, Juliana De Castilhos, Sven Nebelung, and Daniel Truhn - [stanfordnlp/dspy](https://awesome-repositories.com/repository/stanfordnlp-dspy.md) (35,325 ⭐) — DSPy is a declarative programming framework designed for building complex language model applications. It treats model interactions as modular, composable programs, allowing developers to define task logic through typed class schemas rather than relying on manually written prompts. By organizing workflows into hierarchical, reusable Python objects, the framework enables the construction of sophisticated AI systems that manage state and execution flow independently. The framework distinguishes itself through an automated optimization engine that iteratively refines prompt instructions and few-shot demonstrations. By evaluating candidate programs against defined metrics and feedback loops, it systematically improves performance without requiring manual prompt engineering. This process is supported by a programmatic evaluation harness that measures output quality using custom metrics and model-based judges, ensuring consistent behavior across multi-stage pipelines. Beyond core orchestration, the system provides a robust interface for structured data extraction and tool integration. It includes mechanisms for wrapping Python functions as tools, executing iterative reasoning loops, and adapting model outputs into validated data structures. These capabilities are complemented by comprehensive state management and persistence utilities, which allow for the versioning and tracking of program configurations throughout the development lifecycle. - [sahat/hackathon-starter](https://awesome-repositories.com/repository/sahat-hackathon-starter.md) (35,226 ⭐) — This project is a Node.js web application boilerplate designed to accelerate development by providing a pre-configured foundation with integrated routing, templating, and developer tooling. It serves as a comprehensive starter kit that includes a full-stack authentication system, a payment integration starter, and an LLM agent framework. The framework distinguishes itself with specialized tools for AI development, including a retrieval-augmented generation implementation kit with vector search and semantic caching. It enables the creation of reasoning agents featuring tool-calling loops and real-time response streaming via server-sent events, as well as visual input processing for camera feeds. The project covers a broad range of operational capabilities, including multi-provider identity federation with two-factor authentication, subscription payment processing, and document-based state persistence. It also incorporates a quality assurance suite featuring headless browser automation and deterministic API response mocking using recorded fixtures. Additional utility surface includes transactional email delivery, web analytics tracking, and metadata optimization for search engines and social sharing. - [claude-code-best/claude-code](https://awesome-repositories.com/repository/claude-code-best-claude-code.md) (20,272 ⭐) — Claude Code is a command-line interface and multi-agent orchestration framework designed for autonomous software engineering. It enables AI agents to perform codebase modifications, debugging, and Git workflow management while coordinating multiple specialized agents to decompose and execute complex engineering tasks in parallel. The system distinguishes itself through a high degree of isolation and safety, utilizing Git worktrees to create independent working directories for concurrent agents and implementing a tiered permission system that combines user rules, project policies, and OS-level sandboxing. It further extends its reach as an autonomous computer use interface, capable of driving web browsers and operating system interfaces via natural language through screen capture and simulated input. Broad capability areas include Model Context Protocol integration for external tool discovery, advanced context management to optimize token usage and persistent project memory, and remote agent administration via WebSocket bridges for distributed execution. The framework also incorporates atomic file operations with snapshot-based recovery and comprehensive monitoring for API expenditure and tool execution tracing. - [sport-agents/sport-agents](https://awesome-repositories.com/repository/sport-agents-sport-agents.md) (0 ⭐) — SPORT introduces an online self-exploration loop that enables multimodal agents to self-improve via AI-generated tasks and LLM-verified preference tuning without human annotations. - [aishwaryanr/awesome-generative-ai-guide](https://awesome-repositories.com/repository/aishwaryanr-awesome-generative-ai-guide.md) (24,755 ⭐) — This project is a community-driven knowledge repository and technical learning resource focused on the field of generative artificial intelligence. It serves as a centralized hub for developers and practitioners to access curated research, tutorials, and foundational concepts necessary for building and deploying modern artificial intelligence applications. The platform distinguishes itself through a collaborative, distributed contribution model that aggregates diverse learning materials into a structured, searchable knowledge base. It covers a wide range of specialized topics, including retrieval-augmented generation, large language model training, fine-tuning techniques, and agentic workflows. Beyond technical skill development, the repository functions as a professional development hub, offering interview preparation resources and guidance for those pursuing careers in the artificial intelligence industry. The content is organized through a hierarchical taxonomy, allowing users to navigate complex subjects such as system evaluation, multimodal models, and security tools. The repository provides access to comprehensive code notebooks and structured tutorials, all maintained as static documentation within a version control system to ensure accessibility and ease of discovery. - [weitianxin/awesome-agentic-reasoning](https://awesome-repositories.com/repository/weitianxin-awesome-agentic-reasoning.md) (1,275 ⭐) - [brexhq/prompt-engineering](https://awesome-repositories.com/repository/brexhq-prompt-engineering.md) (9,538 ⭐) — This project is a comprehensive guide and framework for large language model prompt engineering. It provides a collection of techniques and patterns for optimizing model responses through structured system prompts, context management, and a variety of implementation patterns. The project focuses on several specialized domains, including the creation of autonomous agents through reasoning loops and the implementation of retrieval augmented generation to inject semantic context into prompts. It also provides methods for enforcing structured outputs in serialization formats like JSON or YAML for programmatic use. The resource covers high-level capabilities such as context window optimization using sliding windows, the definition of model behavior via hidden system prompts, and the use of chain-of-thought reasoning to improve logical accuracy. It further addresses the integration of dynamic data and the enforcement of output citations for information retrieval. - [javascript-tutorial/en.javascript.info](https://awesome-repositories.com/repository/javascript-tutorial-en-javascript-info.md) (25,344 ⭐) — This project is a comprehensive JavaScript programming tutorial and language reference. It serves as a web development education resource providing instruction on modern language fundamentals, object-oriented design, and advanced asynchronous programming patterns. The resource functions as both a frontend development guide and a technical reference. It covers core language features such as closures, prototypes, promises, and typed arrays, while providing practical lessons on managing browser data and handling network requests. The content spans several key capability areas, including browser API integration, data structure manipulation, and frontend web development. It specifically covers the manipulation of the document object model, the handling of browser events, and the creation of reusable web components. The documentation is delivered as a collection of static-site generated pages created from markdown files. - [josh-xt/agent-llm](https://awesome-repositories.com/repository/josh-xt-agent-llm.md) (3,200 ⭐) — AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions. - [onjas-buidl/llm-agent-game](https://awesome-repositories.com/repository/onjas-buidl-llm-agent-game.md) (52 ⭐) — LLM-based autonomous world - [prefecthq/fastmcp](https://awesome-repositories.com/repository/prefecthq-fastmcp.md) (22,994 ⭐) — FastMCP is a Python framework designed for building servers that expose functions, resources, and prompts to AI models using the Model Context Protocol. It simplifies the development process by automatically deriving tool metadata, input schemas, and documentation directly from Python function signatures and type hints. The framework provides a unified container for managing these components, allowing developers to build modular applications that integrate seamlessly with AI assistants. The project distinguishes itself through its support for interactive, server-defined user interface components that render directly within AI chat environments. It includes a dynamic middleware pipeline for injecting cross-cutting concerns like authentication and telemetry, alongside a protocol-agnostic transport layer that supports stdio, HTTP, and server-sent events. These capabilities allow for the creation of rich, stateful interactions that extend beyond simple text-based tool execution. The framework covers a broad capability surface, including comprehensive support for authentication, authorization, and secure deployment. It provides tools for managing long-running tasks, background execution, and complex dependency injection, while offering built-in observability through logging, distributed tracing, and performance monitoring. Developers can also leverage built-in CLI scaffolding and hot-reloading to accelerate the development and testing of server-side logic. FastMCP is distributed as a Python library, with documentation and tooling focused on streamlining the registration and configuration of local server instances for external AI clients. - [addyosmani/agent-skills](https://awesome-repositories.com/repository/addyosmani-agent-skills.md) (60,849 ⭐) — Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated code meets production standards. The system covers a broad range of engineering capabilities, including technical specification automation, multi-axis code reviews, and test-driven development. It also provides frameworks for context management, security auditing, and the orchestration of parallel agent tasks to synthesize findings into consolidated reports. These skills are implemented as standardized instructions and commands that can be loaded into an agent via auto-discovery or explicit installation. - [livekit/livekit](https://awesome-repositories.com/repository/livekit-livekit.md) (19,358 ⭐) — LiveKit is a comprehensive framework for building and orchestrating real-time, multimodal AI agents that interact with users through voice, video, and text. It provides a centralized, event-driven architecture to manage the entire lifecycle of automated participants, from initialization and session state management to graceful shutdown. By utilizing a selective forwarding unit, the platform efficiently routes media streams between participants and agents, ensuring low-latency communication and secure, token-based authentication for all connections. The platform distinguishes itself through its modular pipeline-based media processing, which chains specialized speech-to-text, language, and text-to-speech services into cohesive workflows. It includes advanced capabilities for real-time voice activity detection, enabling natural turn-taking and interruption handling, alongside remote procedure call tooling that allows agents to execute external functions or access local resources during a conversation. Developers can further extend these interactions by integrating photorealistic virtual avatars that synchronize visual expressions with the agent's audio output. Beyond core conversational logic, the system offers extensive support for telephony integration, allowing agents to connect to public networks via SIP for inbound and outbound calling. It provides a robust suite of observability and monitoring tools to track agent performance, connection quality, and session events, ensuring reliability in production environments. The platform also includes specialized utilities for task automation, such as capturing and validating structured user data, and supports multi-step workflow orchestration to handle complex, context-aware interactions. The project provides a command-line interface for scaffolding, deploying, and testing agent applications, with documentation available in machine-readable formats to assist in development. - [pguso/ai-agents-from-scratch](https://awesome-repositories.com/repository/pguso-ai-agents-from-scratch.md) (3,130 ⭐) — This project is an LLM agent framework and orchestration engine designed for building autonomous agents that reason, utilize tools, and execute multi-step plans. It provides a system for implementing the ReAct pattern, which interleaves reasoning and action cycles to solve complex problems through iterative observation and self-correction. The framework includes a tool integration layer that connects language models to external functions and APIs using structured schemas and embedding-based routing. It also features a memory management system to persist conversation history and user preferences, maintaining long-term context across sessions. The orchestration capabilities cover multi-agent coordination, state-based conversation management, and the execution of dependency graphs for deterministic task completion. Additionally, the system supports prompt templating, provider-agnostic model abstractions, and execution auditing to track internal reasoning steps. - [beyond-all-reason/beyond-all-reason](https://awesome-repositories.com/repository/beyond-all-reason-beyond-all-reason.md) (3,991 ⭐) — Main game repository for Beyond All Reason. - [apollographql/reason-apollo](https://awesome-repositories.com/repository/apollographql-reason-apollo.md) (547 ⭐) — Reason binding for Apollo Client and React Apollo - [nndl/llm-beginner](https://awesome-repositories.com/repository/nndl-llm-beginner.md) (6,421 ⭐) — This project is a collection of educational resources and technical guides focused on the development and implementation of large language models. It provides a comprehensive curriculum covering transformer architectures, training methods, and deployment strategies. The materials provide detailed instructions for building autonomous agents using reasoning loops and tool integration, as well as guides for fine-tuning models through supervised learning and preference optimization. It also includes tutorials for constructing retrieval augmented generation pipelines and implementing transformer models from scratch. The project covers a broad range of capabilities, including model architecture design, parameter-efficient tuning, and the creation of vector-based retrieval systems. It further addresses natural language processing tasks such as text classification, semantic analysis, and tokenization, alongside methods for monitoring model performance through execution tracing and attention visualization. - [elves/elvish](https://awesome-repositories.com/repository/elves-elvish.md) (6,325 ⭐) — Elvish is a shell that combines interactive command-line use with a structured scripting language, designed to make both everyday terminal work and automation tasks more predictable and readable. It parses, compiles, and executes code in three phases, catching syntax and variable errors before any code runs, and it aborts execution on command failure by default to prevent silent errors. The shell introduces value-oriented pipelines that pass structured data like lists, maps, and closures between commands, preserving types without serialization. It also mixes traditional byte streams with these value pipes, converts between the two, and processes pipeline data concurrently as each value arrives. Elvish provides readable script syntax without cryptic operators, supports variables, loops, functions, and list iteration, and includes features like directory history navigation, a built-in file manager, and command history search with fuzzy matching. For data handling, Elvish supports JSON serialization and deserialization, nested data structures, list slicing, map indexing, typed number construction, and copy-on-assignment semantics. It offers exception-based error handling, parallel task execution, and wildcard glob expansion. The shell is available as a single statically linked binary with no dependencies, installable via script, manual download, or source compilation. - [sparkjiao/dpo-trajectory-reasoning](https://awesome-repositories.com/repository/sparkjiao-dpo-trajectory-reasoning.md) (0 ⭐) — This repository contains the code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing" (EMNLP 2024).