Top 23 llm-agent Open-Source Projects

1. agenticSeek

   1 2 27,487 8.4 Python

   Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

   

2. AppSignal

   www.appsignal.com sponsored

   AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.

   

3. AutoResearchClaw

   2 3 14,659 9.3 Python

   Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

   

   Project mention: AutoResearchClaw Tries to Turn One Research Idea Into a Draft Paper | dev.to | 2026-04-26

   git clone https://github.com/aiming-lab/AutoResearchClaw.git

4. PocketFlow-Tutorial-Codebase-Knowledge

   3 9 12,699 3.5 Python

   Pocket Flow: Codebase to Tutorial

   

   Project mention: Beyond Code Generation: LLMs for Code Understanding | dev.to | 2026-01-02

   My exploration of LLM-based tools for code understanding started with DeepWiki, which I have been using since its early release. As my interest shifted toward analyzing private repositories and experimenting more deeply with the underlying mechanics, I began looking for open-source alternatives. This led me to deepwiki-rs and later OpenDeepWiki. After starring OpenDeepWiki on GitHub, one of the authors of Davia reached out, which introduced me to a different, more collaborative approach to AI-assisted documentation. I later encountered PocketFlow Tutorial Codebase Knowledge through a technical report, and finally Google Code Wiki when it was publicly announced, which I followed closely given its enterprise positioning.

5. autoharness

   4 1 11,054 9.2 Python

   Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark. (by tigerless-labs)

   

   Project mention: Show HN: Autoharness – a self-learning, maintaining skill layer for Claude Code | news.ycombinator.com | 2026-06-30

6. oasis

   5 4 5,246 8.0 Python

   🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents. (by camel-ai)

   

7. eko

   6 2 4,960 9.3 TypeScript

   Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

   

   Project mention: I built an open-source AI browser that automates web tasks with natural language | dev.to | 2025-11-03

   Special thanks to Eko for the powerful agent framework.

8. mcp-context-forge

   7 8 4,640 9.9 Python

   An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.

   

   Project mention: Every AI toolchain is inventing its own safety layer. We shipped one that works across all of them. | dev.to | 2026-05-12

   Anthropic shipped Claude Code hooks — PreToolUse, PostToolUse, Notification, and friends. They run as subprocesses, get JSON on stdin, and decide whether the tool call proceeds. OpenAI ships tool guardrails in the Agents SDK — Python (and now TS) callables you attach to a tool, with tripwire booleans that abort the run. The MCP ecosystem is sprouting gateways and proxies for the same purpose: MCPX, IBM ContextForge, Microsoft's MCP Gateway, Lasso Security's MCP Gateway — all reasonable answers to the same wire-level question.

9. SaaSHub

   www.saashub.com sponsored

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

10. LLMStack

    8 23 2,311 9.9 Python

    No-code multi-agent framework to build LLM Agents, workflows and applications with your data

    

11. lumibot

    9 44 2,116 9.9 Python

    AI agents that actually place the trade. 12 brokers, real backtests, stocks options futures forex crypto and prediction markets.

    

12. LLMCompiler

    10 3 1,891 7.4 Python

    [ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

    

    Project mention: One Model, Many Roles: Specializing LLM Inference Without Training More Models | dev.to | 2026-09-29

    LLMCompiler studies planned parallel function execution and reports latency improvements of up to 3.7× over ReAct in its evaluated tasks. That supports studying dependency-aware execution; it does not establish the same speedup for several inference roles sharing one backend.

13. ai

    11 8 1,878 9.1 TypeScript

    One-stop shop for building AI-powered products and businesses with Stripe. (by stripe)

    

    Project mention: The Stripe MCP Server — Payment Operations Through Your AI Assistant | dev.to | 2026-03-24

    Stripe's official MCP server connects AI assistants to payment infrastructure — customers, products, invoices, subscriptions, refunds, and uniquely, Stripe's documentation. It lives in the stripe/ai monorepo alongside framework integrations for OpenAI, LangChain, CrewAI, and Vercel AI SDK.

14. awesome-ai-agent-papers

    12 1 1,846 8.2

    A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.

    

    Project mention: Awesome AI Agent Papers 2026 | dev.to | 2026-02-22

    You can view the repository here.

15. mirage

    13 2 1,768 - TypeScript

    A Unified Virtual Filesystem For AI Agents (by strukto-ai)

    

    Project mention: Mirage – Unified Virtual File System for AI Agents | news.ycombinator.com | 2026-05-19

16. Agentlas-OS

    14 1 1,583 9.8 Python

    Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

    

    Project mention: Stop Rebuilding AI Agents for Every Task | dev.to | 2026-07-03

17. TheoremExplainAgent

    15 2 1,501 8.0 Python

    Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]

    

    Project mention: arXivisual – Transform research papers into 3blue1brown style videos | news.ycombinator.com | 2026-02-18

    Neat project but how does this compare to : https://github.com/TIGER-AI-Lab/TheoremExplainAgent

18. Autonomous-Agents

    16 1 1,385 9.4

    Autonomous Agents (LLMs) research papers. Updated Daily.

    

19. best-of-Agent-Harnesses

    17 1 1,112 9.1 Python

    🏆 Ranked list of 167 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.

    

    Project mention: Best-of-Agent-Harnesses – Ranked list of 167 AI agent harnesses, rescored weekly | news.ycombinator.com | 2026-10-01

20. awesome-knowledge-management

    18 5 884 7.8

    A curated list of amazingly awesome articles, people, applications, software libraries and projects related to the knowledge management space

    

21. Foundry

    19 4 873 8.6 Python

    The foundation layer for agentic intelligence. (by promptise-com)

    

    Project mention: Promptise Foundry – a Python agentic framework for building production systems | news.ycombinator.com | 2026-05-04

22. llm-functions

    20 1 777 8.1 Shell

    Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.

    

23. AgentLab

    21 2 645 4.7 Python

    AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

    

    Project mention: How I would run computer use benchmarks properly | dev.to | 2026-10-12

    WebArena's tooling handles this by running tasks in a fixed order, and its maintainers note that dropping the order for more parallelism can cost 1 to 2 percent. OSWorld 2.0 took the other route: it ships 31 self-hosted websites and scopes each attempt's state by cookie, so attempts do not contaminate each other.

24. RSI-Anything

    22 1 562 7.5 HTML

    RSI-Anything: Unlocking Recursive Self-Improvement with World Models

    

    Project mention: Show HN: RSI-Anything – JEPA world models for self-improving agents | news.ycombinator.com | 2026-10-13

25. funes

    23 1 511 9.8 Rust

    Durable, searchable memory of your past agent sessions. (by huggingface)

    

    Project mention: OKF Agent Memory – Git-native persistent memory for AI coding agents | news.ycombinator.com | 2026-09-05

26. SaaSHub

    www.saashub.com sponsored

    SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

    

llm-agents related posts

• CodeAlta, Your Agentic Development Environment

  1 project | news.ycombinator.com | 10 Oct 2026

• Eight broken tool calls: how six agent frameworks recover

  1 project | dev.to | 4 Oct 2026

• One Model, Many Roles: Specializing LLM Inference Without Training More Models

  1 project | dev.to | 29 Sep 2026

• Show HN: Drop – a rootless Linux sandbox with gVisor support

  5 projects | news.ycombinator.com | 22 Sep 2026

• I asked four LLMs to review my code by path. Three invented bugs

  1 project | dev.to | 21 Sep 2026

• LRU is harder to beat than the KV-cache papers suggest

  3 projects | news.ycombinator.com | 10 Sep 2026

• I Gave Claude Code a Brain. Then I Measured What It Costs to Ask for One.

  2 projects | dev.to | 1 Sep 2026
• A note from our sponsor - SaaSHub
  www.saashub.com | 15 Oct 2026

  SaaSHub helps you find the best software and product alternatives Learn more →

Index

Sponsored

AppSignal knows why the f*#k it crashed.

Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.

www.appsignal.com