Projects sharing features with Earendil Works Pi

This project is a comprehensive framework for building, evaluating, and connecting autonomous agent systems. It provides a library of standardized architectural patterns for implementing complex agent workflows, including multi-agent orchestration, iterative reasoning, and memory management. By offering a unified interface for model providers, the framework allows for consistent agent execution across different artificial intelligence services. The framework distinguishes itself through a focus on rigorous benchmarking and deterministic control. It includes a suite of tools for evaluating age

Botpress is a conversational AI builder and LLM agent platform used to design chatbot workflows and orchestrate agents powered by large language models. It provides a framework for managing the entire lifecycle of these agents, from initial creation through to deployment across various production environments. The platform includes a custom integration SDK for developing and publishing third-party connectors that extend agent capabilities. These tools allow for the creation of custom plugins that connect AI agents to external APIs and third-party services. The system supports both visual des

Swarms is a multi-agent orchestration framework and autonomous agent toolkit designed to coordinate large language model agents. It serves as a workflow engine for managing agent relationships, providing the infrastructure to build autonomous agents with integrated memory, tool-calling capabilities, and reasoning loops. The framework is distinguished by its multi-agent consensus systems, which utilize voting, adversarial debates, and judge agents to synthesize high-quality responses. It supports a variety of collaboration patterns, including director-worker hierarchies, expert synthesis, and

This project is a TypeScript SDK and application framework for integrating large language models into software. It provides a unified interface and multi-provider model wrapper to interact with various AI model providers through a single, consistent API. The toolkit includes a generative UI framework and an AI agent orchestrator. These tools enable the creation of autonomous agents capable of executing functions and the development of AI-driven user interfaces with specialized state management for streaming chatbot components. The framework covers broad capability areas including stream-base

Letta is a framework for building, deploying, and managing autonomous AI agents that maintain persistent state across long-term interactions. It provides a comprehensive suite of primitives for defining agents with configurable personas, modular memory blocks, and tool-use capabilities, enabling them to retain user preferences and conversation history over extended sessions. The platform distinguishes itself through its advanced memory management and orchestration capabilities. It allows agents to autonomously update their own memory, perform retrieval-augmented generation, and coordinate com

LazyLLM is a multi-agent framework and orchestration engine designed for building complex AI applications. It provides a system for chaining large language models into sequential or parallel pipelines, utilizing a tool registry to convert standard functions into discoverable tools that models can invoke via reasoning. The project features an application deployment kit that enables hosting model workflows as web services with integrated chat interfaces and API gateways. It includes an infrastructure abstraction layer that allows users to switch between bare-metal servers, clusters, and public

Agency Swarm is a multi-agent orchestration framework and development kit designed to coordinate specialized AI agents through defined communication patterns and handoffs. It functions as a system for managing agent swarms, providing an API gateway to expose these coordinated collectives as production-ready HTTP endpoints. The project distinguishes itself through its Model Context Protocol integration layer, which connects agents to external data sources and capabilities. It implements specialized orchestration patterns, such as the orchestrator-worker model and role-based delegation, to tran

OpenCode is a terminal-based development agent that automates software engineering tasks by integrating artificial intelligence directly into the command-line environment. It functions as an autonomous workflow orchestrator, capable of executing file operations, running shell commands, and applying code patches to complete complex development tasks without manual intervention. The tool distinguishes itself through its ability to index local codebases into vector embeddings, enabling semantic search and natural language queries across project files. It maintains session context through a local

This project is a framework for building AI coding agents that automate software development tasks using large language models. It includes a task lifecycle manager that tracks complex development goals through a persistent graph of dependent tasks and a system for multi-agent orchestration to delegate tasks to specialized sub-agents. The framework implements a Model Context Protocol client to discover and execute tools from external servers and provides a remote development bridge to synchronize local command line interfaces with remote containers or desktop environments. The system covers

Manifest is a language model provider unification system that standardizes access to multiple AI backends through a single interface. It functions as a centralized management layer for integrating various cloud-based and local model providers to simplify how applications request completions. The system provides intelligent model routing and high availability infrastructure by directing queries based on complexity and automatically triggering model fallbacks when a primary provider fails. It distinguishes itself through multi-tenant AI management, organizing agents into isolated groups with de

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 m

Superduper is an AI agent development kit and LLM application framework designed to build autonomous agents and data-driven applications. It functions as a RAG orchestration platform and vector search infrastructure, coordinating AI models with database storage to perform multi-step computations and actions using persisted data states. The project distinguishes itself by providing a database-integrated machine learning pipeline that executes training and inference tasks directly on data hosted within SQL and NoSQL databases. It allows for the deployment of self-hosted AI infrastructure on pri

Devika is an autonomous AI software engineering system designed to plan, write, and debug code from high-level natural language instructions. It functions as an agentic software engineer that decomposes complex objectives into actionable coding steps for autonomous execution. The system integrates cloud-based and self-hosted large language models through a provider-agnostic layer, allowing for multi-model reasoning and code completion. It distinguishes itself by combining these models with a sandboxed execution environment for running code across different operating systems and a web-browsing

OpenAgent is an autonomous AI agent framework designed to orchestrate language models and retrieved context to execute complex user goals. It functions as a platform for building autonomous agents that utilize iterative loops to select tools and process information. The project features a multi-model gateway that abstracts various large language model providers, allowing users to switch between models on a per-conversation basis without modifying code. It also includes a RAG knowledge base system that ingests documents and generates embeddings to provide semantic context during inference. Th

AdalFlow is an autonomous AI agent framework and LLM application library designed for building modular workflows. It serves as a model-agnostic interface and RAG pipeline orchestrator, allowing users to develop ReAct agents that utilize iterative reasoning and external tool execution to solve complex tasks. The project distinguishes itself through a prompt optimization system that uses textual gradient descent to automatically refine prompt templates and few-shot examples. It treats model feedback as a differentiable signal, enabling a form of LLM backpropagation to iteratively improve output

Yao is an LLM agent framework and low-code web app builder designed for orchestrating autonomous AI agents. It provides a platform to design, deploy, and coordinate agents with specialized personas that can plan tasks, utilize external tools, and execute multi-stage pipelines. The project distinguishes itself through a Model Context Protocol server for connecting assistants to external binaries and HTTP services, and a gRPC remote execution engine that allows agents to manage remote servers and devices. It includes a model-agnostic provider bridge that supports dynamic switching between vario

This project is an LLM autonomous agent framework and orchestration tool designed to build goal-driven agents that automate complex workflows. It functions as a system for converting high-level objectives into a series of autonomous actions and managing the coordination of multiple specialized agents to solve multi-step problems. The framework features a tool integration layer that parses structured model outputs into executable functions and external API calls. It utilizes a non-blocking execution pipeline to manage task orchestration through recursive loops and asynchronous event handling.

jcode is a framework for developing autonomous AI coding agents that automate software development tasks. It functions as an agent orchestrator, tool runtime, and semantic memory engine, enabling the creation of agents that can modify code, run tests, and iterate on their own functionality. The project is distinguished by its use of recursive agent swarming, where a hierarchy of collaborating agents can spawn child agents to decompose complex tasks. It implements a semantic memory system that combines vector-based retrieval with graph-based relationship mapping to maintain context across sess

ACE Framework is an open-source software framework designed for building autonomous artificial intelligence agents that operate entirely on local hardware without relying on cloud services. The system executes complete cognitive loops locally, allowing agents to reason, plan, and execute complex tasks independently. The architecture separates core reasoning, planning, memory, and task execution into discrete functional modules while maintaining long-term agent memory and contextual data locally to preserve continuity across operational sessions. It includes a unified interface layer that dec

Koog is an LLM agent framework used to build autonomous entities that execute tool-based workflows. It utilizes a graph-based workflow engine to define agent behaviors and decision paths as a directed graph of nodes and edges. The framework distinguishes itself through a model provider orchestrator that enables dynamic switching, load balancing, and automatic fallbacks between different AI backends. It implements the Model Context Protocol to connect agents to remote tool servers and features a RAG memory system using vector embeddings to maintain long-term conversation context. The project

Guardrails is a Python SDK that wraps calls to large language models with configurable validation pipelines, corrective actions, and structured output generation. It provides a unified API layer that connects to over 100 language models, applying consistent validation, streaming, and error-handling across providers. The framework validates and corrects model responses against safety and quality rules, detecting and mitigating risks in both inputs and outputs using pre-built and custom validators. The project distinguishes itself through a validator-pipeline architecture that sequentially appl

Multica is an autonomous coding agent manager and LLM agent orchestration platform. It coordinates teams of autonomous agents to execute coding tasks and manage their lifecycles through a centralized dashboard. The system provides multi-tenant agent workspaces that isolate agents, settings, and project issues into distinct organizational boundaries. The platform distinguishes itself through an agent skill library that captures successful task solutions as reusable, versioned skills. These skills are shared across the agent team and pinned using content hashes to ensure consistent behavior acr

x-cmd is an AI agent orchestrator, cloud infrastructure CLI, and cross-platform package manager that provides an enhanced POSIX shell toolkit. It integrates large language models directly into the terminal for chatting, code generation, and the execution of agentic workflows, while offering a framework for building interactive terminal user interface components. The project distinguishes itself by deploying containerized AI agents within isolated sandboxes, provisioning them with specialized skills and headless browser automation capabilities. It further streamlines development through a unif

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 sof

This project is an autonomous agent workflow engine and multi-agent orchestration framework. It provides a runtime for managing agent lifecycles and a provider-agnostic abstraction layer for interacting with multiple large language model backends through standardized requests and structured outputs. The framework features a reliability layer for output verification, utilizing sampling-based majority voting and generator-evaluator feedback loops to refine model responses. It supports complex coordination patterns including sequential chaining, parallel execution with fan-in aggregation, and re

AutoGPT-Next-Web is a browser-based dashboard designed for the configuration, deployment, and monitoring of autonomous artificial intelligence agents. It provides a centralized interface for managing agent lifecycles and task execution, allowing users to orchestrate complex workflows through a unified platform. The platform distinguishes itself by acting as a secure, access-controlled portal that protects management tools and execution logs behind mandatory authentication codes. It features a provider abstraction layer that routes requests to multiple artificial intelligence services, enablin

This project is a framework for managing generative AI services through a unified provider interface and adapter layer. It provides a standardized API for calling multiple cloud-based and locally hosted models, translating provider-specific parameters and responses into a uniform format. The system includes an agent orchestrator designed for long-running tasks, featuring state persistence for resuming runs and execution tracing to monitor decision-making processes. It integrates the Model Context Protocol to connect models to external servers and filesystems and employs a policy-based executi