AI Agents: open-source projects on GitHub
1319 repositories on AI Agents, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
GPU TERMINAL FOR CODING
Native macOS terminal with GPU rendering, persistent sessions, and coding-agent workflow support. Enables SSH connections, runs as a daemon and CLI tool on Linux, and opt
★ 309 · SwiftSESSION-KNOWLEDGE LOCAL KNOWLEDGE BASE
The project stores Claude Code session history in a local SQLite database and provides 13 MCP tools for search. Indexing runs on pure Python standard library, and no data
★ 307 · PythonRUNTM: ISOLATED SANDBOXES
Open sandbox for AI agents: isolated environments where Claude Code and Cursor write and deploy code.
★ 306 · PythonEMULO: CODE LOGS ANALYSIS
Collect Claude Code and Codex logs into a local you.md profile, turning them into a smart AI agent.
★ 306 · PythonAGENT MEMORY SYNCHRONIZATION
MemoSync enables co-managing memory with coding agents across sessions. Local workbench for Claude Code, Codex, Pi and OpenCode.
★ 306 · TypeScriptCLAY - MULTIPLEXER COLLABORATIVE CODE
Self-hosted multi-user workspace for Claude Code and Codex: shared memory, browser, multi-user editing.
★ 305 · JavaScriptREMINAL WORKSPACE IN BROWSER
Closed the lid and walked away — every window, desktop and terminal on your machines run in any browser. End‑to‑end encryption, no open ports, no client or account requir
★ 305 · GoUNIVERSAL EPISODIC MEMORY
Engrim — a local project SQLite memory for AI agents. Supports working with Antigravity, Claude Code, Cursor, Windsurf and Codex without cloud attachment.
★ 305 · PythonOrchestKit Full AI Package
Full-stack AI in TypeScript: 114 skills, 37 agents, 212 hooks. Build production apps in minutes.
★ 304 · TypeScriptSAFE RUNTIME FOR AI AGENTS
The runtime project provides an isolated execution environment based on WebAssembly for running untrusted AI-agent code. It offers a sandbox with restricted access to the
★ 304 · RustINFINITE CANVAS FOR TERMINALS
Desktop application allowing visual management of terminals on an infinite canvas. TypeScript.
★ 303 · TypeScriptBrowser-Based SaaS Reverse Engineering
An agent skill that reverse engineers SaaS products via browser automation into a structured knowledge base covering screens, business rules, data models, design tokens,
★ 300 · JavaScriptMISTGATE: SELF-HOSTED VPN PANEL
Mistgate is a beta panel for sharing VPN (Hysteria2, VLESS REALITY, AmneziaWG) with family and team. Servers added via browser over SSH, client health checks and Telegram
★ 300 · GoHIVEMIND – UNIFIED BRAIN FOR AGENTS
TypeScript project that unifies all your AI agents into a single intelligent network.
★ 298 · TypeScriptRUSSIAN TEXT FOR AI AGENTS
ru-text evaluates Russian text for AI agents on a 0–10 scale, cleaning neuroslop and applying typography to GOST. It checks style and uses 2000+ linguistic atoms.
★ 298 · ShellALL SKILLS FOR AI AGENTS
awesome-skills — community of Apify agent skills for AI coding assistants. 252⭐, Python, includes ready‑made skills for actors, agents and MCP workflows.
★ 298 · PythonAGENTDECK: CONTROL AI AGENT ANYWHERE!
AI agent control panel with support for Stream Deck+, mobile devices, and ESP32 displays. One interface for code, terminal, and visualization.
★ 297 · CONE CLI FOR ALL ROBOTS!!!
quackd — CLI for bot control with LLM brain. Connects Microduck, LeRobot, ROS and others, works with Claude, OpenAI, Gemini, Grok or locally via Ollama/vLLM. Includes sim
★ 297 · PythonMULTI-REPO ARCHITECTURE FOR AI AGENTS
Open-source tool for multi-repo architecture discovery. Creates .arch.md files and centralizes them for AI agent context and onboarding. Works with GitHub, GitLab, CodeCo
★ 297 · PythonSEMANTIC GIT FOR AI CODING
Intent turns Git into a semantic layer for AI agents. The tool understands change context, not just diffs, and syncs agent memory with commit history. Python CLI for Clau
★ 295 · PythonGUILD: Context and Memory for AI Agents
A single Go binary with SQLite and hybrid search for task coordination and shared context among coding AI agents.
★ 294 · GoSHIP STUDIO: DEVELOPMENT WITHOUT LIMITS
Ship Studio is a local-first development environment where you can write, test, and deploy code without leaving the app. It works with any CLI‑based coding agent such as
★ 294 · TypeScriptPERSISTENT AI AGENT MEMORY
AgentRecall-MCP gives AI agents long-term memory, learns from mistakes, and compresses context to save tokens.
★ 292 · TypeScriptAGENT METHODOLOGY FOR SOLO
Project bigpowers turns years of engineering experience into ready agent skills for solo developers. Automates routine via Bmad, Claude Code and Cursor Rules. 216 stars o
★ 292 · ShellOPEN SOURCE RAG FOR LEGAL PRECEDENTS
CaseCite — self-hosted platform for RAG search over caselaw and document analysis. Deploy your own AI assistant for legal research without sending data to the cloud. Writ
★ 292 · PythonMCP SERVER FOR AUTOCAD
Autocad-MCP — MCP server for AI agents (Claude, Cursor). 240+ tools to draw, edit, read DWG/DXF. Live AutoCAD via COM or headless with ezdxf. Mechanical sheets, P&ID, flo
★ 291 · PythonMEMORY FOR AI AGENTS
Local persistent memory for Claude Code, Cursor, and Codex via MCP. Solutions, lessons, and facts are stored in a single SQLite file — fully offline and multilingual.
★ 289 · PythonBLACK BOX FOR AI CODE
brain0 links every commit to agent prompts. Detects drift, audits agent data access (DLP), assesses risk from evidence, stores MCP memory, and emits signed provenance att
★ 289 · RustAI Engineer Interview Prep Kit
Curated interview questions, study maps, and coding challenges for AI/LLM engineering roles with company-specific sets and worked solutions.
★ 289 · PythonUTEKE: BRAIN FOR AI
Local memory for AI agents: semantic search, storage and recall of memories in one Rust binary with no configuration.
★ 288 · RustMIMEO: 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 · PythonMONITORING OF CODE AGENTS IN TERMINAL
agtop is a top‑style TUI utility that displays the activity of AI agent sessions (Claude Code, Codex CLI, etc.) in real time. It lets you track token usage, task progress
★ 288 · JavaScriptPCTX - Secure Sandbox for Agents
pctx automatically transforms agent tools and MCP servers into executable code that runs in isolated sandboxes, reducing token consumption.
★ 287 · RustARC GENTIC: GATES FOR AI AGENTS
Arcgentic provides planning, development and external audit gates for AI agents. Role router sets interaction topology. MCP‑UI panel shows status in real‑time, and the Cl
★ 285 · PythonEIGENWISE TOOLSHED: PLUGINS FOR CLAUDE
Six Claude Code plugins for frequently recurring tasks: repository maps, conditional rules, ticketed parallel work, extra subscription models, local usage metrics, and gu
★ 285 · TypeScriptOPEN CONSTRUCTION COST DATABASE
Multilingual construction cost database for AI agents: 55K+ items, 27K+ resources, 30 regions, semantic search via Qdrant.
★ 284 · HTMLALPACA 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 · PythonPAXM: Memory for AI Agents
PAXM provides persistent, provider‑neutral memory for agents Codex, Claude Code, OpenCode, Pi, and MCP, written in Go.
★ 283 · GoMNEMORY: MEMORY FOR AI AGENTS
Self-hosted, secure, feature-rich memory for AI agents and assistants. Extracts facts intelligently, removes duplicates and stores artifacts with full content.
★ 283 · PythonSEARCHARVESTER: AI AGENT SEARCH AND FETCH
Self‑hosted search engine based on SearXNG (100+ sources) with FastAPI and trafilatura. Tavily‑compatible /search and /extract endpoints with size limits and pagination,
★ 283 · PythonPLUGINS AND MODS FOR CLAUDE CODE
Collection of plugins and mods improving Claude Code workflow. Includes prompt queue for sequential task execution and agent customization tools. 211 stars on GitHub.
★ 282 · TypeScriptSECURITYCLAW AUTONOMOUS SOC AGENT
Modular SOC agent on Python, monitors OpenSearch/Elasticsearch, builds RAG memory and validates anomalies with LLMs.
★ 280 · Python3D OFFICE FOR CLAUDE CODE
Visualize AI agent work in an interactive 3D space. Dashboard shows files, terminal, and Claude Code activity in real time.
★ 280 · JavaScriptMCP SERVERS FOR LATIN AMERICA
Open-source MCP servers for commerce in Latin America: Pix, NF-e, banking, logistics and messengers. 252 stars, MIT.
★ 279 · JavaScriptOPENBROWSER AI: BROWSER AUTOMATION
A framework for smart browser automation: an LLM generates Python code, controlling the page via CDP.
★ 279 · PythonPAPERGRAPH MCP: READING MATH WITHOUT GUESSING
PaperGraph MCP converts arXiv math papers into structured knowledge maps: it extracts theorems, links proofs to their sources, and sets a reading order. It lets AI agents
★ 279 · PythonLLM AGENTS IN SCALA
llm4s is a library for building LLM agents in Scala with type safety. Supports Anthropic, Gemini, and Java interop. 272 stars on GitHub.
★ 279 · ScalaMemory Techniques for LLM
30 notebooks with examples of memory implementation for language models: from simple buffers to knowledge graphs.
★ 277 · Jupyter NotebookSUPER LOCAL AI MEMORY
First local AI memory without cloud or API, achieving 74% retrieval accuracy and 60% zero-LLM on LoCoMo.
★ 277 · PythonAWESOME LLM WIKI: AI BASE GUIDE
awesome-llm-wiki is a curated list of foundational blueprints, frameworks, and guides for building self‑expanding AI‑compiled knowledge bases. The project helps you quick
★ 277PROFILER FOR AI AGENTS AND LLM
Graphsignal Profiler is a tool for debugging and monitoring inference. It helps find performance bottlenecks in deep neural networks and AI agents. Perfect for working wi
★ 276 · PythonAGNIX — Linter for AI Assistants
Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, and MCP with auto-fixes. Plugin for all popular IDEs.
★ 274 · RustDASHCLAW: WALL FOR AI AGENTS
DashClaw intercepts AI agent actions and provides security policies. 273 stars on GitHub.
★ 273 · JavaScriptENTERPRISE AI AGENT
Platform for registering business APIs as AI capabilities in Java/Spring Boot: creating agents via GraphSpec, MCP/A2A/Gateway and monitoring execution.
★ 273 · JavaLIVING AGENT ORGANISM IN LISP
nodecode is a framework for autonomous AI agents in Common Lisp. Implements a "living organism" concept: the agent plans, writes code, runs tests, and fixes errors in a l
★ 273 · Common LispAegis: AI Agent Architecture Control
Makes AI agents architecture-aware: first establishes a baseline, then verifies evidence, controls drift, and ensures safety in long-running tasks.
★ 272 · ShellRust Web Crawler for AI
High-performance Rust crawler extracting clean Markdown and structured data for AI agents and RAG pipelines. Supports PDF/RSS parsing, browser rendering, and Firecrawl-co
★ 272 · RustROSETTA: META‑PROMPTING FOR AGENTS
Rosetta simplifies creating and centralizing prompts for AI coding agents, using meta‑prompting and contextual engineering.
★ 271 · PythonHYPERLOOM AUTO-OPTIMIZATION LLM ON AMD
Hyperloom — agentic system that automatically optimizes LLM workloads on AMD GPUs by selecting kernels and tuning parameters for peak performance without manual setup.
★ 271 · PythonOPENAPI CATALOG FOR AI AGENTS
Thousands of public APIs in OpenAPI format. Every spec is machine-readable and scored for AI agents. CC0 license — free to use.
★ 271New projects on this topic in Telegram
Telegram →