A curated list of frameworks, tools, and resources for building and deploying AI agents.
See the code
A curated list of frameworks, tools, libraries, platforms, and resources for building and deploying AI agents.
Built by the community — add your project
Frameworks for building and managing AI agents.
| Framework | Stars | Description |
|---|---|---|
| AutoGen |  | Multi-agent conversations, GPT-4 integration, customizable workflows |
| AutoGPT |  | Autonomous AI agent for task completion, web browsing, and code execution |
| MetaGPT |  | Simulates software company workflows, role-based agents |
| Neurolink |  | Multi-provider AI agent framework, unifies 12+ LLM providers, workflow orchestration |
| CrewAI |  | Role-based agent orchestration, task delegation |
| PraisonAI |  | Fastest multi-agent framework (3.77μs), 100+ LLMs, MCP, workflows, Python & JS SDKs |
| LightAgent |  | Lightweight Python agent framework with memory, MCP/SSE, Skills, streaming, and LightSwarm multi-agent collaboration |
| LangChain |  | Tool integration, memory management, agent chaining |
| LangGraph |  | Stateful, multi-actor applications with LLMs |
| SuperAGI |  | Open-source AGI framework, multi-modal agents |
| Google ADK (Agent Development Kit) |  | Code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents |
| OpenAI Assistants API (SDK) |  | Build AI assistants with tools and persistent threads via SDK |
| AgentOps |  | Monitoring, cost tracking, and benchmarking SDK for agents |
| AgentField |  | Open-source control plane for AI agents at scale, with routing, memory, observability, identity, and auth |
| Agentset |  | Production-ready RAG platform with agentic reasoning, hybrid search, and multimodal support |
| LLMStack |  | No-code multi-agent framework with data workflows |
| Agency Swarm |  | Reliable multi-agent orchestration using OpenAI Assistants API |
| AGiXT |  | Adaptive automation platform with persistent memory |
| Upsonic |  | Reliability layer, model context protocol, task-oriented |
| Taskade |  | AI-native workspace for building and deploying multi-agent workflows |
| Taskade MCP |  | Open-source MCP toolkit and integrations for building AI agents and automated workflows |
| AgentVerse |  | Multi-agent simulation environments for research |
| ChatDev |  | Collaborative software development agents |
| Agno |  | Multi-agent framework, runtime, and control plane for AI products |
| Agentlas OS |  | Apache-2.0 local-first agent OS for portable agent and team packages, cross-host orchestration, MCP/A2A, and verification gates |
| Composio |  | 100+ integrations for AI agents via function calling, MCP compatible |
| PocketFlow |  | Minimalist 100-line LLM framework for agents, workflows, and RAG |
| CAMEL |  | Multi-agent framework for communicative agents research |
| Strands Agents SDK |  | AWS-backed model-driven agent SDK with MCP and multi-provider support |
| Summoner |  | Agent-to-agent networking for server-decoupled agents over long-lived TCP sessions (Python/Rust), 50+ runnable templates |
| KodeAgent |  | The Minimal Agent Engine to build ReAct & CodeAct agents, with support for code sandbox and observability |
| Hivemoot Colony |  | Self-governing multi-agent platform; agents propose, vote, peer-review, and ship software via democratic consensus |
| OIXA Protocol |  | Agent-to-agent economic marketplace protocol on Base with on-chain escrow and A2A integrations |
| smolagents |  | Code-first agent library by Hugging Face, model-agnostic with MCP and sandbox support |
| LlamaIndex |  | Data framework for LLM apps with RAG, agents, and 300+ integrations |
| Mastra |  | TypeScript AI framework for agents, workflows, MCP servers, and evals |
| Hivekeep |  | Self-hosted platform to run a team of specialized AI agents with persistent memory, a web UI, and Telegram/Slack/Discord/Matrix channels, in a single Bun and SQLite container |
| Orkas |  | Local-first workspace coordinating specialist AI agents across projects |
| Better Agent |  | Source-available workspace for running and supervising Claude, Codex, and Gemini coding-agent sessions |
| fractal |  | Hierarchical coding-agent runtime with bounded autonomous loops, recursive delegation, isolated Git worktrees, persistent SQLite state, and live operator controls |
| YYLO |  | Command-line orchestrator for coding agents with typed task, validation, merge, and release-readiness boundaries, a dedicated branch/worktree, and risk-based merge review |
| SandBase Harness |  | Local-first, self-hosted TypeScript agent runtime and MCP bridge with sandboxed sessions and audit/replay |
| Tale |  | Self-hosted workspace for people and AI agents, with shared project tasks, manager delegation, persistent sandbox workspaces, and human review of results |
| Raven |  | Plans a complex task as a DAG and runs it across built-in and third-party agents, with a self-evolving loop that installs only verified changes |
| Markus |  | Platform for building and running teams of AI agents with roles, task delegation, and persistent memory |
Agents designed for specific tasks or industries.
| Name | Stars | Description |
|---|---|---|
| SWE-agent |  | AI agent for software engineering tasks |
| GPT Pilot |  | Assists in writing and debugging code |
| OpenHands |  | Open-source AI software development agents (formerly OpenDevin) |
| Devika |  | Agentic AI Software Engineer that writes code from natural instructions |
| Aider |  | AI pair programming in terminal |
| Plandex |  | AI coding engine for complex projects |
| TaskWeaver |  | Code-first agent framework for analytical tasks |
| Gemini CLI |  | Open-source AI agent bringing Gemini to the terminal with MCP support |
| AgenticSeek |  | Fully local autonomous agent that browses web and codes without APIs |
| Cline |  | Autonomous coding agent in VS Code with MCP, browser use, and terminal |
| Goose |  | Open-source extensible AI agent by Block for engineering tasks |
| bolt.diy |  | AI-powered full-stack web development in the browser with 19+ LLMs |
| Atomic Agent |  | Local-first CLI and TUI coding agent, open-weight models, 56 tools, MCP |
| Orbi |  | Takes a labeled GitHub issue to a reviewed PR and a tagged release |
| Name | Stars | Description |
|---|---|---|
| GPT Researcher |  | Autonomous agent for comprehensive research |
| Dr. Claw |  | Local research workspace with survey, ideation, experiment, publication, and promotion stages |
| Storm |  | Multi-agent system for collaborative reasoning |
| DeerFlow |  | Framework for deep research with web search and Python execution |
| Agon |  | Prompt Economy orchestrator: reusable scientist/coder/auditor loops instead of per-task prompts, 18 roles, 10+ disciplines |
| AutoNumerics |  | Writes, debugs, and validates classical PDE numerical solvers from plain-language problem descriptions |
| Caesar |  | Builds a knowledge graph while exploring the web, then refines drafts via adversarial synthesis |
| P2PCLAW |  | Decentralized P2P agent swarm for open scientific research |
| CAJAL |  | Local scientific paper generation agent with IMRaD structure and citations |
| Name | Stars | Description |
|---|---|---|
| ShortGPT |  | Short-form video generation agent |
| AI-town |  | Virtual world simulation with AI agents |
| BulkPublish |  | API and agent skills for drafting, scheduling, and publishing social media content |
| Name | Stars | Description |
|---|---|---|
| Browser Use |  | Make websites accessible for AI agents, automate tasks with ease |
| NanoBrowser |  | TypeScript-based AI browsing agent |
| Firecrawl |  | Turn websites into LLM-ready markdown or structured data |
| Crawl4AI |  | Open-source LLM-friendly web crawler and scraper |
| Stagehand |  | AI browser automation framework with natural language and code |
| Xquik |  | X/Twitter data and action API (REST, MCP, webhooks) that agents call for search, monitoring, and posting |
| Skyvern |  | Browser automation agent using LLMs and computer vision to complete web workflows |
| Playwright MCP |  | MCP server exposing Playwright browser automation to AI agents |
| Agent S |  | Open framework for computer-use agents that operate desktop GUIs like a human |
| UI-TARS Desktop |  | GUI agent by ByteDance that controls desktop and browser via natural language, built on the UI-TARS vision model |
| agent-qa |  | Self-improving QA agent for natural-language web and mobile tests |
Agents and frameworks specialized for specific programming languages.
| Name | Language | Stars | Description |
|---|---|---|---|
| TypeChat | TypeScript |  | Type-safe LLM outputs using TypeScript types |
| LangChain.js | JavaScript |  | JS version of LangChain |
| Semantic Kernel | C#/.NET |  | Integrate LLMs into .NET apps |
| LangChain4j | Java |  | Java implementation of LangChain |
| Haystack | Python |  | Search and question answering agents |
| LlamaIndex.js | TypeScript |  | JS version of LlamaIndex |
| LangChain.rb | Ruby |  | Ruby implementation of LangChain |
| LangChainGo | Go |  | Go implementation for LLM orchestration |
| OpenAI Agents (Python) | Python |  | Lightweight, provider-agnostic agent framework |
| Swarms-rs | Rust |  | Swarm-based agent orchestration in Rust |
| AnythingLLM | JavaScript |  | All-in-one AI agent builder with RAG and UI |
Frameworks for building real-time voice and conversational AI agents.
| Name | Stars | Description |
|---|---|---|
| Pipecat |  | Open-source framework for building real-time voice and multimodal conversational agents |
| LiveKit Agents |  | Framework for real-time voice AI agents with WebRTC transport, built on LiveKit |
| TEN Framework |  | Open-source framework for real-time conversational voice agents with multimodal support |
Tools and systems for managing AI agents.
| Name | Stars | Description |
|---|---|---|
| Letta (formerly MemGPT) |  | Dynamic, adaptive agent memory system |
| Mem0 |  | Universal memory layer for AI agents |
| Tree Ring Memory |  | Local-first CLI/TUI for agent memory recall, forgetting, audit, and consolidation |
| ChromaDB |  | Vector DB for memory/context |
| Weaviate |  | Scalable vector DB for semantic memory |
| Portable Handoff |  | Local-first CLI for handing off coding-agent session context between tools |
| Mnemoverse |  | MIT MCP memory server; a hosted engine re-ranks recall from reported outcomes |
| Fidelis Memory |  | Local-first MCP memory: local vector recall, optional keyword+vector hybrid mode |
| Screenpipe |  | Source-available screen/audio history for agents via MCP and a local API |
| Busabase |  | Open-source agent workspace with auditable, permission-aware ChangeRequests |
| Name | Stars | Description |
|---|---|---|
| AgentBench |  | Multi-environment testing for agents |
| LangTrace |  | Monitoring and trace visualization |
| agenttrace |  | Local TUI and reports for AI coding agent session cost, latency, failures, and health |
| ax |  | Local-first evidence graph for coding-agent sessions, tool calls, skills, and cost |
| Agent Evaluation |  | Benchmarking agent capabilities |
| Simple Evals |  | OpenAI's lightweight LLM evaluation library |
Tracing, monitoring, and debugging tools for agents in production.
| Name | Stars | Description |
|---|---|---|
| Langfuse |  | Open-source LLM engineering platform for tracing, prompt management, and evaluations |
| Arize Phoenix |  | Open-source AI observability with OpenTelemetry tracing, evals, and agent debugging |
| Helicone |  | Open-source LLM observability with one-line integration for cost and usage tracking |
| OpenLLMetry |  | OpenTelemetry-based instrumentation for LLM and agent frameworks |
| Laminar |  | Open-source platform for tracing and evaluating AI agents |
| Noveum Trace |  | Python SDK for tracing LLM calls and agent workflows in the hosted Noveum platform |
| OrcaReplay |  | Records a coding-agent run below the harness and replays it offline byte-for-byte |
| OpenClaw Monitor |  | Open-source monitoring dashboard for OpenClaw AI agents — token usage, session tracking, 7-day trends |
| Bifrost |  | OpenAI-compatible LLM gateway with multi-provider routing, failover, and tracing |
| Name | Stars | Description |
|---|---|---|
| Daytona |  | Elastic infrastructure for AI-generated code |
| E2B |  | Secure sandboxed environments for agents |
| OctoAI |  | Scalable infrastructure for agent deployment |
| Modal |  | Serverless runtime for AI workloads |
| Name | Stars | Description |
|---|---|---|
| Agent Governance Toolkit |  | Policy enforcement, zero-trust identity, and execution sandboxing for autonomous AI agents |
| Garak |  | LLM vulnerability scanner - probes for prompt injection, data leakage, and hallucination |
| Presidio |  | PII detection, redaction, and anonymization across text, images, and structured data |
| Guardrails AI |  | Output validation and guardrails for LLM responses |
| NeMo Guardrails |  | Programmable guardrails for LLM-based conversational systems |
| LLM Guard |  | Security toolkit for scanning and sanitizing LLM prompts and outputs |
| Polaxis |  | Pre-execution runtime firewall for AI agents - 7-layer threat detection and spend controls |
| sofagent |  | Commit-time audit harness for coding agents - git-diff rules, HMAC audit trail, rollback |
| hermes-jailbench |  | Deterministic jailbreak regression benchmark for known-pattern attacks |
| LintLang |  | Zero-LLM static analysis for agent configs, tool descriptions, and prompts |
| Little Canary |  | Sacrificial-canary prompt-injection preflight (block / flag / pass) |
Open protocols and implementations for agent-to-tool and agent-to-agent interoperability.
| Name | Stars | Description |
|---|---|---|
| Model Context Protocol |  | Anthropic's open protocol standardizing how AI agents connect to tools and data sources |
| MCP Servers |  | Official collection of reference MCP server implementations |
| A2A |  | Open protocol started by Google for agent-to-agent communication across frameworks |
| FastMCP |  | Pythonic framework for building MCP servers and clients |
Key research papers, benchmarks, and surveys on AI agents.
| Title | Link | Description |
|---|---|---|
| The Rise of LLM-Based Agents | arXiv | Comprehensive survey on LLM-based agents |
| Tool Learning with Foundation Models | arXiv | Tool usage in AI agents |
| Multi-Agent Collaboration | arXiv | Collaboration in multi-agent systems |
| Large Language Model based Multi-Agents | arXiv | Survey of progress and challenges |
| Agentic AI Systems | arXiv | Components and applications of agentic AI |
| A Survey on LLM-based Autonomous Agents | arXiv | Focus on autonomous LLM agents |
| OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents | arXiv | Four-agent pipeline with bandit scheduling turns optimization problems into solver code |
| Training Agents to Evolve with Their Harness (HAT) | arXiv | Harness-aware training for a live-commerce agent, with evaluation on changing skills, tools, prompts, and hooks |
| The Agent Loop: A Survey of Control Strategies, Skills, and Harnesses | SSRN | Control strategies, agentic RL, termination and recovery, skills, and harnesses around the agent loop |
| Name | Stars | Description |
|---|---|---|
| ToolBench |  | Benchmark for tool learning |
| SOTOPIA-π |  | Social intelligence benchmark for multi-agent systems |
| PerspectiveGap |  | Benchmark for writing orchestration prompts in multi-agent systems, 110 scenarios across 10 topologies |
| ClawBench |  | Live-web browser-agent benchmark with 283 tasks across 163 real websites |
Join the conversation and stay updated on AI agent developments.
| Name | Link | Description |
|---|---|---|
| LangChain Community | Discord | Active developer community |
| AutoGen Discussions | GitHub | Microsoft AutoGen community forum |
| AgentOps Discord | Join | Developer space for observability and testing agents |
| Letta AI Community | Discord | Discussions on adaptive memory in AI agents |
| Name | Link | Description |
|---|---|---|
| The Batch (DeepLearning.AI) | Subscribe | Weekly AI industry insights |
A huge thank you to all our amazing contributors!
Your contributions make this project better every day.
⭐ A special shoutout to all our stargazers for your support! Star this repository to stay updated and help grow the community of AI enthusiasts!
Your contributions are welcome! Here's how to get started:
README.md.For more details, see the CONTRIBUTING.md guide.
138 followers · starred Jun 2026
A curated list of frameworks, tools, and resources for building and deploying AI agents.
See the code
A curated list of frameworks, tools, libraries, platforms, and resources for building and deploying AI agents.
Built by the community — add your project
Frameworks for building and managing AI agents.
| Framework | Stars | Description |
|---|---|---|
| AutoGen | | Multi-agent conversations, GPT-4 integration, customizable workflows |
| AutoGPT | | Autonomous AI agent for task completion, web browsing, and code execution |
| MetaGPT | | Simulates software company workflows, role-based agents |
| Neurolink | | Multi-provider AI agent framework, unifies 12+ LLM providers, workflow orchestration |
| CrewAI | | Role-based agent orchestration, task delegation |
| PraisonAI | | Fastest multi-agent framework (3.77μs), 100+ LLMs, MCP, workflows, Python & JS SDKs |
| LightAgent | | Lightweight Python agent framework with memory, MCP/SSE, Skills, streaming, and LightSwarm multi-agent collaboration |
| LangChain | | Tool integration, memory management, agent chaining |
| LangGraph | | Stateful, multi-actor applications with LLMs |
| SuperAGI | | Open-source AGI framework, multi-modal agents |
| Google ADK (Agent Development Kit) | | Code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents |
| OpenAI Assistants API (SDK) | | Build AI assistants with tools and persistent threads via SDK |
| AgentOps | | Monitoring, cost tracking, and benchmarking SDK for agents |
| AgentField | | Open-source control plane for AI agents at scale, with routing, memory, observability, identity, and auth |
| Agentset | | Production-ready RAG platform with agentic reasoning, hybrid search, and multimodal support |
| LLMStack | | No-code multi-agent framework with data workflows |
| Agency Swarm | | Reliable multi-agent orchestration using OpenAI Assistants API |
| AGiXT | | Adaptive automation platform with persistent memory |
| Upsonic | | Reliability layer, model context protocol, task-oriented |
| Taskade | | AI-native workspace for building and deploying multi-agent workflows |
| Taskade MCP | | Open-source MCP toolkit and integrations for building AI agents and automated workflows |
| AgentVerse | | Multi-agent simulation environments for research |
| ChatDev | | Collaborative software development agents |
| Agno | | Multi-agent framework, runtime, and control plane for AI products |
| Agentlas OS | | Apache-2.0 local-first agent OS for portable agent and team packages, cross-host orchestration, MCP/A2A, and verification gates |
| Composio | | 100+ integrations for AI agents via function calling, MCP compatible |
| PocketFlow | | Minimalist 100-line LLM framework for agents, workflows, and RAG |
| CAMEL | | Multi-agent framework for communicative agents research |
| Strands Agents SDK | | AWS-backed model-driven agent SDK with MCP and multi-provider support |
| Summoner | | Agent-to-agent networking for server-decoupled agents over long-lived TCP sessions (Python/Rust), 50+ runnable templates |
| KodeAgent | | The Minimal Agent Engine to build ReAct & CodeAct agents, with support for code sandbox and observability |
| Hivemoot Colony | | Self-governing multi-agent platform; agents propose, vote, peer-review, and ship software via democratic consensus |
| OIXA Protocol | | Agent-to-agent economic marketplace protocol on Base with on-chain escrow and A2A integrations |
| smolagents | | Code-first agent library by Hugging Face, model-agnostic with MCP and sandbox support |
| LlamaIndex | | Data framework for LLM apps with RAG, agents, and 300+ integrations |
| Mastra | | TypeScript AI framework for agents, workflows, MCP servers, and evals |
| Hivekeep | | Self-hosted platform to run a team of specialized AI agents with persistent memory, a web UI, and Telegram/Slack/Discord/Matrix channels, in a single Bun and SQLite container |
| Orkas | | Local-first workspace coordinating specialist AI agents across projects |
| Better Agent | | Source-available workspace for running and supervising Claude, Codex, and Gemini coding-agent sessions |
| fractal | | Hierarchical coding-agent runtime with bounded autonomous loops, recursive delegation, isolated Git worktrees, persistent SQLite state, and live operator controls |
| YYLO | | Command-line orchestrator for coding agents with typed task, validation, merge, and release-readiness boundaries, a dedicated branch/worktree, and risk-based merge review |
| SandBase Harness | | Local-first, self-hosted TypeScript agent runtime and MCP bridge with sandboxed sessions and audit/replay |
| Tale | | Self-hosted workspace for people and AI agents, with shared project tasks, manager delegation, persistent sandbox workspaces, and human review of results |
| Raven | | Plans a complex task as a DAG and runs it across built-in and third-party agents, with a self-evolving loop that installs only verified changes |
| Markus | | Platform for building and running teams of AI agents with roles, task delegation, and persistent memory |
Agents designed for specific tasks or industries.
| Name | Stars | Description |
|---|---|---|
| SWE-agent | | AI agent for software engineering tasks |
| GPT Pilot | | Assists in writing and debugging code |
| OpenHands | | Open-source AI software development agents (formerly OpenDevin) |
| Devika | | Agentic AI Software Engineer that writes code from natural instructions |
| Aider | | AI pair programming in terminal |
| Plandex | | AI coding engine for complex projects |
| TaskWeaver | | Code-first agent framework for analytical tasks |
| Gemini CLI | | Open-source AI agent bringing Gemini to the terminal with MCP support |
| AgenticSeek | | Fully local autonomous agent that browses web and codes without APIs |
| Cline | | Autonomous coding agent in VS Code with MCP, browser use, and terminal |
| Goose | | Open-source extensible AI agent by Block for engineering tasks |
| bolt.diy | | AI-powered full-stack web development in the browser with 19+ LLMs |
| Atomic Agent | | Local-first CLI and TUI coding agent, open-weight models, 56 tools, MCP |
| Orbi | | Takes a labeled GitHub issue to a reviewed PR and a tagged release |
| Name | Stars | Description |
|---|---|---|
| GPT Researcher | | Autonomous agent for comprehensive research |
| Dr. Claw | | Local research workspace with survey, ideation, experiment, publication, and promotion stages |
| Storm | | Multi-agent system for collaborative reasoning |
| DeerFlow | | Framework for deep research with web search and Python execution |
| Agon | | Prompt Economy orchestrator: reusable scientist/coder/auditor loops instead of per-task prompts, 18 roles, 10+ disciplines |
| AutoNumerics | | Writes, debugs, and validates classical PDE numerical solvers from plain-language problem descriptions |
| Caesar | | Builds a knowledge graph while exploring the web, then refines drafts via adversarial synthesis |
| P2PCLAW | | Decentralized P2P agent swarm for open scientific research |
| CAJAL | | Local scientific paper generation agent with IMRaD structure and citations |
| Name | Stars | Description |
|---|---|---|
| ShortGPT | | Short-form video generation agent |
| AI-town | | Virtual world simulation with AI agents |
| BulkPublish | | API and agent skills for drafting, scheduling, and publishing social media content |
| Name | Stars | Description |
|---|---|---|
| Browser Use | | Make websites accessible for AI agents, automate tasks with ease |
| NanoBrowser | | TypeScript-based AI browsing agent |
| Firecrawl | | Turn websites into LLM-ready markdown or structured data |
| Crawl4AI | | Open-source LLM-friendly web crawler and scraper |
| Stagehand | | AI browser automation framework with natural language and code |
| Xquik | | X/Twitter data and action API (REST, MCP, webhooks) that agents call for search, monitoring, and posting |
| Skyvern | | Browser automation agent using LLMs and computer vision to complete web workflows |
| Playwright MCP | | MCP server exposing Playwright browser automation to AI agents |
| Agent S | | Open framework for computer-use agents that operate desktop GUIs like a human |
| UI-TARS Desktop | | GUI agent by ByteDance that controls desktop and browser via natural language, built on the UI-TARS vision model |
| agent-qa | | Self-improving QA agent for natural-language web and mobile tests |
Agents and frameworks specialized for specific programming languages.
| Name | Language | Stars | Description |
|---|---|---|---|
| TypeChat | TypeScript | | Type-safe LLM outputs using TypeScript types |
| LangChain.js | JavaScript | | JS version of LangChain |
| Semantic Kernel | C#/.NET | | Integrate LLMs into .NET apps |
| LangChain4j | Java | | Java implementation of LangChain |
| Haystack | Python | | Search and question answering agents |
| LlamaIndex.js | TypeScript | | JS version of LlamaIndex |
| LangChain.rb | Ruby | | Ruby implementation of LangChain |
| LangChainGo | Go | | Go implementation for LLM orchestration |
| OpenAI Agents (Python) | Python | | Lightweight, provider-agnostic agent framework |
| Swarms-rs | Rust | | Swarm-based agent orchestration in Rust |
| AnythingLLM | JavaScript | | All-in-one AI agent builder with RAG and UI |
Frameworks for building real-time voice and conversational AI agents.
| Name | Stars | Description |
|---|---|---|
| Pipecat | | Open-source framework for building real-time voice and multimodal conversational agents |
| LiveKit Agents | | Framework for real-time voice AI agents with WebRTC transport, built on LiveKit |
| TEN Framework | | Open-source framework for real-time conversational voice agents with multimodal support |
Tools and systems for managing AI agents.
| Name | Stars | Description |
|---|---|---|
| Letta (formerly MemGPT) | | Dynamic, adaptive agent memory system |
| Mem0 | | Universal memory layer for AI agents |
| Tree Ring Memory | | Local-first CLI/TUI for agent memory recall, forgetting, audit, and consolidation |
| ChromaDB | | Vector DB for memory/context |
| Weaviate | | Scalable vector DB for semantic memory |
| Portable Handoff | | Local-first CLI for handing off coding-agent session context between tools |
| Mnemoverse | | MIT MCP memory server; a hosted engine re-ranks recall from reported outcomes |
| Fidelis Memory | | Local-first MCP memory: local vector recall, optional keyword+vector hybrid mode |
| Screenpipe | | Source-available screen/audio history for agents via MCP and a local API |
| Busabase | | Open-source agent workspace with auditable, permission-aware ChangeRequests |
| Name | Stars | Description |
|---|---|---|
| AgentBench | | Multi-environment testing for agents |
| LangTrace | | Monitoring and trace visualization |
| agenttrace | | Local TUI and reports for AI coding agent session cost, latency, failures, and health |
| ax | | Local-first evidence graph for coding-agent sessions, tool calls, skills, and cost |
| Agent Evaluation | | Benchmarking agent capabilities |
| Simple Evals | | OpenAI's lightweight LLM evaluation library |
Tracing, monitoring, and debugging tools for agents in production.
| Name | Stars | Description |
|---|---|---|
| Langfuse | | Open-source LLM engineering platform for tracing, prompt management, and evaluations |
| Arize Phoenix | | Open-source AI observability with OpenTelemetry tracing, evals, and agent debugging |
| Helicone | | Open-source LLM observability with one-line integration for cost and usage tracking |
| OpenLLMetry | | OpenTelemetry-based instrumentation for LLM and agent frameworks |
| Laminar | | Open-source platform for tracing and evaluating AI agents |
| Noveum Trace | | Python SDK for tracing LLM calls and agent workflows in the hosted Noveum platform |
| OrcaReplay | | Records a coding-agent run below the harness and replays it offline byte-for-byte |
| OpenClaw Monitor | | Open-source monitoring dashboard for OpenClaw AI agents — token usage, session tracking, 7-day trends |
| Bifrost | | OpenAI-compatible LLM gateway with multi-provider routing, failover, and tracing |
| Name | Stars | Description |
|---|---|---|
| Daytona | | Elastic infrastructure for AI-generated code |
| E2B | | Secure sandboxed environments for agents |
| OctoAI | | Scalable infrastructure for agent deployment |
| Modal | | Serverless runtime for AI workloads |
| Name | Stars | Description |
|---|---|---|
| Agent Governance Toolkit | | Policy enforcement, zero-trust identity, and execution sandboxing for autonomous AI agents |
| Garak | | LLM vulnerability scanner - probes for prompt injection, data leakage, and hallucination |
| Presidio | | PII detection, redaction, and anonymization across text, images, and structured data |
| Guardrails AI | | Output validation and guardrails for LLM responses |
| NeMo Guardrails | | Programmable guardrails for LLM-based conversational systems |
| LLM Guard | | Security toolkit for scanning and sanitizing LLM prompts and outputs |
| Polaxis | | Pre-execution runtime firewall for AI agents - 7-layer threat detection and spend controls |
| sofagent | | Commit-time audit harness for coding agents - git-diff rules, HMAC audit trail, rollback |
| hermes-jailbench | | Deterministic jailbreak regression benchmark for known-pattern attacks |
| LintLang | | Zero-LLM static analysis for agent configs, tool descriptions, and prompts |
| Little Canary | | Sacrificial-canary prompt-injection preflight (block / flag / pass) |
Open protocols and implementations for agent-to-tool and agent-to-agent interoperability.
| Name | Stars | Description |
|---|---|---|
| Model Context Protocol | | Anthropic's open protocol standardizing how AI agents connect to tools and data sources |
| MCP Servers | | Official collection of reference MCP server implementations |
| A2A | | Open protocol started by Google for agent-to-agent communication across frameworks |
| FastMCP | | Pythonic framework for building MCP servers and clients |
Key research papers, benchmarks, and surveys on AI agents.
| Title | Link | Description |
|---|---|---|
| The Rise of LLM-Based Agents | arXiv | Comprehensive survey on LLM-based agents |
| Tool Learning with Foundation Models | arXiv | Tool usage in AI agents |
| Multi-Agent Collaboration | arXiv | Collaboration in multi-agent systems |
| Large Language Model based Multi-Agents | arXiv | Survey of progress and challenges |
| Agentic AI Systems | arXiv | Components and applications of agentic AI |
| A Survey on LLM-based Autonomous Agents | arXiv | Focus on autonomous LLM agents |
| OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents | arXiv | Four-agent pipeline with bandit scheduling turns optimization problems into solver code |
| Training Agents to Evolve with Their Harness (HAT) | arXiv | Harness-aware training for a live-commerce agent, with evaluation on changing skills, tools, prompts, and hooks |
| The Agent Loop: A Survey of Control Strategies, Skills, and Harnesses | SSRN | Control strategies, agentic RL, termination and recovery, skills, and harnesses around the agent loop |
| Name | Stars | Description |
|---|---|---|
| ToolBench | | Benchmark for tool learning |
| SOTOPIA-π | | Social intelligence benchmark for multi-agent systems |
| PerspectiveGap | | Benchmark for writing orchestration prompts in multi-agent systems, 110 scenarios across 10 topologies |
| ClawBench | | Live-web browser-agent benchmark with 283 tasks across 163 real websites |
Join the conversation and stay updated on AI agent developments.
| Name | Link | Description |
|---|---|---|
| LangChain Community | Discord | Active developer community |
| AutoGen Discussions | GitHub | Microsoft AutoGen community forum |
| AgentOps Discord | Join | Developer space for observability and testing agents |
| Letta AI Community | Discord | Discussions on adaptive memory in AI agents |
| Name | Link | Description |
|---|---|---|
| The Batch (DeepLearning.AI) | Subscribe | Weekly AI industry insights |
A huge thank you to all our amazing contributors!
Your contributions make this project better every day.
⭐ A special shoutout to all our stargazers for your support! Star this repository to stay updated and help grow the community of AI enthusiasts!
Your contributions are welcome! Here's how to get started:
README.md.For more details, see the CONTRIBUTING.md guide.
138 followers · starred Jun 2026