Open-source alternatives to Pua

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

This project is a Python framework for building autonomous, event-driven agent systems. It provides a unified runtime for orchestrating multi-agent workflows, managing persistent conversation state, and executing code within secure, isolated sandbox environments. The framework is designed to handle complex task delegation, allowing agents to invoke other agents as tools while maintaining context across multi-turn interactions. The framework distinguishes itself through its deep integration with the Model Context Protocol, enabling agents to connect to external data sources and remote services

This project is an AI-powered IDE extension and LLM coding assistant that provides a conversational interface for generating, refactoring, and debugging code. It functions as an AI agent framework and a Model Context Protocol client, connecting AI models to external data sources and tools to automate complex development tasks. The system is distinguished by its use of autonomous AI agents capable of multi-step task execution, including the ability to read files, modify code, and run terminal commands iteratively. It supports recursive agent orchestration through subagent delegation and employ

This project is an agentic development framework and autonomous software engineering system. It utilizes a coordinated network of specialized LLM agents to automate the full software development lifecycle, from codebase exploration and architectural planning to implementation and automated refactoring. The system is distinguished by an agentic memory system and a test-driven development orchestrator. It maintains project continuity across sessions by capturing architectural learnings and state in a persistent semantic database and enforces code quality through an automated cycle of generating

vibe-vibe is an LLM agent engineering framework and toolchain optimizer designed for orchestrating multi-agent systems. It serves as a comprehensive guide and methodology for transforming conceptual ideas into deployed applications through agentic software engineering. The project focuses on the orchestration of specialized AI agent roles with defined collaboration boundaries and iterative feedback loops. It provides frameworks for toolchain optimization, including the selection and evaluation of protocols that extend model capabilities and the design of standardized tool interfaces. The sys

cmux is a GPU-accelerated terminal emulator and workspace manager designed for coordinating multiple concurrent AI coding agents. It functions as an orchestration terminal that uses scriptable workspaces and split panes to manage parallel AI agent workflows, while also serving as a headless browser automation tool and a remote development relay. The project differentiates itself through a programmatic control plane using a Unix domain socket and CLI, allowing for the automated management of terminal layouts and input delivery. It features an integrated web engine for programmatic DOM manipula

The BeeAI Framework is an LLM agent framework and multi-agent orchestration engine used to build autonomous agents that coordinate reasoning, tool execution, and complex workflows. It functions as a structured AI output controller and RAG integration library, providing a unified interface to manage multiple language model providers. The framework is distinguished by its implementation of the Model Context Protocol, allowing agents, tools, and models to be shared between different AI platforms and hosted as agentic tooling servers. It enables the design of collaborative agent teams through dec

This project provides a system for managing agent context and session memory, featuring an agent context compactor, an AI session memory manager, and a tool output sandbox. It functions as a middleware layer and server extension for the Model Context Protocol to optimize context windows and reduce token usage. The system optimizes agent performance by sandboxing tool outputs and externalizing large data sets, replacing raw I/O with pointers and concise summaries. It employs a persistent knowledge base that indexes session history and tool outputs for retrieval via full-text search, ensuring s

DeepCode is an agentic development framework designed to orchestrate autonomous AI agents for software engineering tasks. It functions as a multi-agent workflow orchestrator that translates natural language requirements into functional codebases by coordinating specialized agents for architectural planning, intent analysis, and implementation. The platform integrates multiple language models to power these automated routines, providing a unified environment for complex development projects. The system distinguishes itself through its ability to transform academic research papers into executab

HowToBeAProgrammer is a comprehensive software engineering career guide and professional development framework. It serves as a curated-knowledge repository and handbook designed to help programmers acquire technical habits and social competencies necessary for professional advancement. The project distinguishes itself by integrating technical craftsmanship with a detailed manual for technical leadership and organizational navigation. It provides specific strategies for career progression, such as compensation negotiation, promotion readiness, and the management of professional boundaries to p

The agent-framework is an LLM agent orchestration framework and multi-agent workflow engine designed for building autonomous AI agents. It provides a tool integration layer for binding external functions, APIs, and sandboxed code as executable tools for language models. The framework distinguishes itself through a graph-based system for designing sequential and parallel task flows, featuring state management and checkpointing for long-running processes. It implements comprehensive conversational state management and an observability suite that uses telemetry to trace execution flows and monit

AG2 is a multi-agent large language model orchestration framework, agentic workflow automation tool, and RAG-enabled agent platform. It functions as a communication protocol and framework for coordinating multiple AI agents to solve complex tasks through shared state and standardized messaging. The project distinguishes itself through flexible coordination strategies, including hierarchical agent organization, hub-and-spoke models, and dynamic routing that analyzes conversation context to distribute work. It implements multi-stage feedback loops for iterative refinement and uses schema-constr

This project is a research-oriented repository that serves as a centralized database for system-level prompts and internal behavioral instructions extracted from various large language models. Its primary purpose is to provide a transparent, accessible reference for researchers and developers to study how artificial intelligence models are configured, constrained, and governed. The repository distinguishes itself by cataloging the hidden directives and operational guidelines that define model personas and safety boundaries. By archiving these instruction sets, it enables comparative analysis

XAgent is an autonomous agent system that decomposes complex goals into sequential subtasks for execution via a planner and actor model. It functions as a collaboration framework that integrates human-in-the-loop workflows, allowing users to provide real-time guidance and missing information during the automation process. The system features a containerized tool sandbox to isolate the execution of shells and browsers, ensuring system safety and consistency. It includes a state-based execution recorder that captures snapshots of agent runs to enable the exact reproduction of specific task sequ

Paperclip is an LLM agent orchestration platform and governance suite designed to coordinate teams of autonomous AI agents. It provides a management plane for defining organizational hierarchies, assigning roles, and aligning individual agent tasks with a structured mission tree to ensure work maps to business objectives. The project distinguishes itself through a specialized agent skill registry and workspace manager. It allows for the discovery and injection of reusable workflows into agent runtimes without retraining and provides isolated, sandboxed execution environments with persistent s

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

DeepSeek-R1 is an open-weights large language model focused on advanced reasoning. It uses chain-of-thought processing and internal monologues to solve complex mathematical and logical problems by breaking tasks into sequential, verifiable thought processes. The model is developed using reinforcement learning to optimize reasoning patterns and verify logical steps. It employs a distillation process to transfer these high-performance logic capabilities from a large teacher model into smaller, computationally efficient versions. The training framework incorporates group relative policy optimiz

OpenSkills is an agent capability orchestrator and skill manager designed to sync, version, and distribute standardized skill definitions across autonomous agent environments. It functions as a system for installing domain-specific instruction sets and specialized knowledge into large language model agents, acting as a context injector to load task-oriented prompts and technical documentation into an agent's active operational window. The project distinguishes itself through a git-based distribution framework, allowing agent capabilities to be fetched and updated from remote version control s

This project is an agentic workflow orchestrator and skill registry designed to extend the capabilities of coding assistants and command-line interfaces. It functions as a centralized framework for managing, distributing, and executing modular instruction sets, playbooks, and plugin bundles across diverse development and infrastructure environments. The system distinguishes itself through a declarative approach to automation, utilizing manifest-driven dependency resolution to map specific capabilities to project requirements. By employing file-system-based injection and modular bundling, it a

Quivr is a retrieval-augmented generation platform designed to transform raw documents into searchable knowledge bases. It functions as a centralized environment where users can ingest files, index them into vector databases, and interact with language models to receive contextually relevant, data-backed responses. The platform distinguishes itself through an agentic workflow orchestrator that sequences retrieval tasks, tool execution, and model interactions to resolve complex, multi-step queries. This engine is entirely configuration-driven, allowing users to define document ingestion, chunk

Beads is a versioned, dependency-aware graph database designed for distributed issue tracking and project management. It functions as an agentic workflow orchestrator, providing a structured environment where tasks, dependencies, and project metadata are linked through relational hierarchies. By maintaining a persistent, version-controlled record of project state, the system enables teams to manage complex work items across multiple repositories and environments. The platform distinguishes itself through its deep integration with automated coding agents, acting as a Model Context Protocol ser

Awesome-codex-subagents is an artificial intelligence agent framework designed to orchestrate complex software development workflows. It functions as a library of pre-configured subagents that provide targeted expertise for various phases of the software project lifecycle, allowing developers to manage intricate tasks by delegating responsibilities to specialized, isolated units. The system distinguishes itself through a configuration-driven approach to agent routing and behavior. By utilizing schema-based capability definitions, it ensures consistent interaction between the host environment

This project is an autonomous software development assistant and project management tool that utilizes a multi-agent orchestrator to automate complex workflows. It functions as an agentic framework designed to research, plan, execute, and verify software development tasks by coordinating specialized agents that manage context windows and system performance. The system distinguishes itself through a structured, interview-based requirement engineering phase that clarifies project objectives before initiating automated work. It employs atomic task decomposition to break goals into independent un

Memori is an AI agent memory middleware platform designed to provide persistent, context-aware recall for language models. It functions as a non-intrusive layer that intercepts outbound model requests to automatically capture interaction history and execution traces, ensuring that agents maintain continuity across sessions without requiring modifications to existing application logic. The platform distinguishes itself through a dual-model storage architecture that maintains information as both structured relational primitives for precise fact retrieval and rolling narrative summaries for situ

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 feat

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 coo

Warp is an AI-integrated terminal emulator designed to automate software development workflows directly within the command-line interface. It functions as an enterprise-grade orchestration platform that coordinates multiple artificial intelligence models and coding agents to assist with building, reviewing, and shipping code. By embedding these capabilities into the shell, the environment allows developers to prompt, plan, and refine software projects without leaving their terminal session. The platform distinguishes itself through a centralized control plane that manages, secures, and scales