LLM Agents: open-source projects on GitHub
78 repositories on LLM Agents, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
POCKET FLOW: CODE IN LESSON
Pocket Flow turns any codebase into clear learning materials, automating tutorial creation.
★ 12,349 · PythonAUTOHARNESS: SELF-LEARNING AGENT
Autoharness is a self‑configuring skill layer for Claude Code that extracts abilities from your real sessions and updates them as you work.
★ 11,125 · PythonGateway for AI Agents
AI Gateway, registry, and proxy server for unifying MCP, A2A, and REST/gRPC API with centralized management, guardrails, and plugins.
★ 3,727 · PythonREDAMON: AI PENTEST FRAMEWORK
Open‑source AI pentest framework: builds attack surface graph, autonomously exploits it in Kali sandbox with human approval and creates PR with fixes. MCP integration: co
★ 3,400 · PythonVIBE-CODING TOOLKIT: AI AGENTS
vibe-coding-toolkit — a battle‑tested set of AI‑coding tools from production: Claude Code plugins, sub‑agent orchestration, quality gates, and ready‑to‑copy prompts. 409
★ 2,424 · JavaScriptAWESOME LANGGRAPH: EVERYTHING UNDER MEASURE
Complete catalog of LangChain+LangGraph: QT concepts, projects, tools, and templates for LLM and multi-agent systems.
★ 2,043 · JavaScriptVirtual FS for AI Agents
Unified virtual file system enabling AI agents to transparently work with files via a single abstract layer.
★ 1,883 · TypeScriptCYBERPUNK AI AGENT FOR WINDOWS
Capri is a cyberpunk AI agent for Windows with voice and screen control. Supports Claude Code, Ollama, DeepSeek, Discord calls and desktop automation. 761 stars on GitHub
★ 1,716 · PythonAI - Building Future with Stripe
A platform for rapidly building AI products with Stripe integration, from prototype to monetization in minutes.
★ 1,600 · TypeScriptTOP-100 AI AGENT HARNESSES
A weekly updated list of 100+ top harnesses for AI agents with an MCP server and ready-to-use recommendation formats.
★ 1,523 · Python80+ AI Agents in Python
Over 80 ready‑to‑use examples of AI agents in Python: autonomous agents, multi‑agent systems, and integration with uAgents, ASI:One, LangChain, and other frameworks.
★ 1,471 · PythonAGENTLAS-OS: Agents Environment
Manage specialist agents via a hub, automatically creating orchestrators for tasks. Works locally and is compatible with any model.
★ 1,458 · PythonSOVEREIGN AI SECURITY AGENTS INFRASTRUCTURE
Open-source infrastructure for deploying sovereign AI security agents. Agents continuously find, verify, and fix vulnerabilities in code, web applications, dependencies,
★ 1,437 · TypeScriptAI-AGENT FOR SECURITY
0 — open-source AI security agent that autonomously detects, exploits and fixes vulnerabilities in the stack. Research preview from Swiss Applied AI & Cybersecurity Resea
★ 1,356 · TypeScriptAUTONOMOUS LLM AGENTS
A collection of research papers on LLM-based autonomous agents. Updated daily — 1311 stars on GitHub.
★ 1,311PAPERJURY - AI Review
The AI agent paperjury runs a pre‑submission stress test of manuscripts: review, verdict, edits, and verification in seconds.
★ 1,221 · JavaScriptSelf‑Evolving Data Ontology
Plugin that builds and continuously updates an ontology layer for data agents, enabling Claude Code/Codex to reason over evolving knowledge.
★ 1,213 · PythonPYTHON SDK FOR AI AGENTS
Library for building AI agents with the full power of Google Antigravity. 1178 stars ⭐
★ 1,178 · PythonLLM AGENTS FOR TRADING
Curated list of LLM agents, MCP servers, and skills for market research, strategies, and trade execution. 319 ⭐
★ 1,006FOUNDRY: AGENT FOUNDATION
Foundry — base layer for creating intelligent agents in Python. Allows quickly building agent‑oriented systems.
★ 897 · PythonCurated Computer-Use Agent Resources
Open catalog of computer-use agents with reviewed papers, GUI models, datasets, benchmarks, and tools. Includes reusable JSONL and SQLite data.
★ 880 · PythonMOBILEGYM: ANDROID AGENT TRAINING
MobileGym is a browser‑hosted Android emulator for research on mobile GUI agents. The platform provides verifiable evaluation and highly parallel online reinforcement‑lea
★ 866 · PythonAI Agents Learning Path
A structured learning path for AI agents with practice and reading. Trilingual (Traditional Chinese / Simplified Chinese / English) and open for community contributions.
★ 843 · PythonMASCOT: Multi-Agent Assistant
MASCOT is a multi-agent socially collaborative assistant presented at EMNLP 2026. The project is implemented in Python and has already garnered 518★.
★ 804 · PythonResidual Memory Context Compaction
Remory trains a residual memory module to compact long contexts into shorter representations for transformer models.
★ 746 · Pythonopen-computer-use - Start Agent for PC Control
open-computer-use — an agent with 82% success in OSWorld, production-ready, runs locally and remotely with a single API key.
★ 738 · TypeScriptORCA REPLAY: TIME TRAVEL
OrcaReplay records any launch of an AI agent and allows you to replay it step by step. You can create forks for experiments and debug the state at each stage, using any m
★ 727 · TypeScriptLLM4AD_NEXT: EASY ALGORITHM DESIGN
A platform for automatic algorithm design featuring an intuitive UI and real‑time collaboration with LLM‑based AI agents.
★ 720 · PythonAuto code exploration
Turns the codebase into an investigative loop: defines metrics, creates benchmarks, and launches parallel search.
★ 706 · PythonSkill corpus for agents
The project collects SKILL.md files into a single searchable skill catalog for AI agents, enabling fast search and automatic task-matching evaluation.
★ 703 · PythonFLUJO: Multi-Agent Automation
FLUJO is a framework for building self‑learning multi‑agents and automating workflows in TypeScript.
★ 675 · TypeScriptCORAL: Multi-agent Evolution
CORAL is a lightweight infrastructure for autonomous self-evolution of multi-agent systems, designed for automated research. Compatible with Claude Code, Codex, Cursor, O
★ 668 · PythonCAMBIUM — FOUNDATION FOR LLM CORPORA
Standard management and tooling for LLM-supported knowledge in Cambium.
★ 664 · PythonPERSISTENT MEMORY FOR AGENTS
funes stores AI agent session history in a searchable LanceDB database. Lets you find context from past dialogues and code in milliseconds. Written in Rust, integrates wi
★ 594 · RustORACLE3: PAPER‑TRADING ENGINE FOR PREDICTION MARKETS
Oracle3 is a paper‑trading engine and MCP server for prediction markets Kalshi and Polymarket. It checks for absence of arbitrage between related contracts, accounting fo
★ 569 · PythonMOBIUS: RUST FRAMEWORK FOR AGENTS
Möbius is a compact Rust framework for building code-writing agents. Frontend-agnostic and works with any LLM. Already gained 300 GitHub stars.
★ 547 · RustPaperOrchestra AI Scientific Writer
Automatic AI author of scientific articles based on the Google PaperOrchestra implementation. Works with any code agent without API keys or LLM SDK.
★ 545 · PythonFLIDE: INSTANT DECISION INFERENCE
Flide is a decision model inference engine with CUDA support. Provides deterministic inference for Gemma and other models in microseconds. Ideal for AI agents requiring s
★ 501 · PythonOPENVLHARNESS: VISUAL AGENTS WITH MEMORY
OpenVLHarness is a framework for evaluating and building visual agents with multimodal memory. It supports real-world tool-use scenarios and complex reasoning chains.
★ 499 · PythonCORDUM - Manage AI Agents
Cordum is an open control plane for AI agents: pre‑execution policy, approval gates, and audit trail. Compatible with LangChain, CrewAI, MCP.
★ 485 · GoPrecision Physics Toolkit
Provides certified computational tools and house engines for exact, high‑precision physics and quantitative science, designed to be driven by LLM agents.
★ 446 · PythonHARNESS-RSI: AGENT SELF-EVOLUTION & EVALUATION
Harness-RSI is a bibliographic project on recursive AI agent self-improvement. Contains theory, evaluation methods, evidence, and bilingual reading list. 431 GitHub stars
★ 446 · TeXAgent Environment Framework
Framework for building realistic reinforcement learning environments with collaboration tools for researchers and engineers.
★ 438 · PythonOPENCHART: TRADING PLATFORM WITH AI
OpenChart - an open-source trading workspace in TypeScript where you can plug in your AI agents and analyze markets with interactive Chart.js charts. It supports exchange
★ 377 · TypeScriptAI AGENTS 2026: TOP 300
300+ ready-made AI agents, frameworks, and tools for code, voice, research, and enterprise. Comparisons, benchmarks, and in-depth reviews.
★ 358LEMMALOG: DATALOG FOR AGENT MEMORY
Lemmalog — a Datalog engine for LLM agent memory. It supports stratified rules, provenance‑tracked facts, incremental derivation, and an MCP server that lets you use the
★ 348 · RustOCTOPODA-OS — MEMORY FOR AI AGENTS
An open OS for AI agents with persistent memory, semantic search, and crash recovery.
★ 342 · Python7×6 Agent Framework
28 agent architecture patterns with working Python code and snippets from Claude Code, Aider, and others.
★ 342 · HTMLCODEALTA: AI ASSISTANT FOR CODING
C# CLI tool with agentic AI for efficient code-writing automation directly in the terminal.
★ 338 · C#50X CLAUDE USAGE FOR $20
cheap-ag multiplies Claude limits 50x. A cheap model writes code, tests decide what merges. One MCP server for Claude Code, no $20 limits.
★ 331 · TypeScriptNAC: HARNESS FOR AGENTS AND TASKS
nac — open-source harness in Rust for executing long-running tasks of AI agents. It uses a central orchestrator, threads, and structured episodes to keep work aligned wit
★ 314 · RustFRIESTRADER AUTOMATED TRADING BOT
FriesTrader — fully automated AI‑bot for trading via Robinhood Agentic Trading MCP. Executes real orders under strict, auditable risk rules that the model cannot override
★ 312 · PythonMini-Verl on One GPU
The project allows running a documented subset of verl-style OPD on a single consumer GPU, using typed configuration, Parquet prompts, and PEFT scaling artifacts.
★ 311 · PythonAGENT MEMORY SYNCHRONIZATION
MemoSync enables co-managing memory with coding agents across sessions. Local workbench for Claude Code, Codex, Pi and OpenCode.
★ 306 · TypeScriptREAL USE CASES HERMES AGENT
awesome-hermes-usecases — curated collection of real-world use cases for Hermes Agent, the self‑improving AI agent from Nous Research. Each example is backed by primary s
★ 296 · PythonGET YOUR FREE DOMAIN
PublicFreeSuffix offers free domain names via DNS technologies. Uses AI for stability and speed.
★ 291MIMEO: TURN ANY EXPERT INTO AN AGENT
Create AGENT.md and SKILL.md from expert knowledge in your repository. Mimeo analyzes code, documentation, and practices, turning them into instructions for AI agents. Su
★ 288 · PythonALPACA TRADING AGENT
AlpacaTradingAgent — a multi-agent LLM framework for automated trading via Alpaca API. It supports market data analysis, trading signal generation, and order execution in
★ 284 · PythonMemory Techniques for LLM
30 notebooks with examples of memory implementation for language models: from simple buffers to knowledge graphs.
★ 277 · Jupyter NotebookGRACE: AI CODE WITH KNOWLEDGE GRAPHS
An open set of agent skills for code generation by contracts with semantic markup and knowledge graphs.
★ 268 · TypeScriptNew projects on this topic in Telegram
Telegram →