SG-Tree / GitHub Social Proof
sg-tree.eu / directory / ai-agent

AI Agents & LLM Frameworks Telemetry Index

Inspect GitHub star velocity, fork-to-star equilibrium, and cold-start traction benchmarks across open-source AI agent runtimes, RAG pipelines, and coding assistants.

All ReposMCP ServersAI AgentsDevToolsInfra & SRECLI ToolsTypeScriptPythonRustGo
Indexed Open-Source Repositories (433)
holaboss-ai/holaOS TypeScript ai-agent 1K+ BENCHMARK

An Open Agent Computer for ANY digital work.

11,452 | 917 (8.0%) | 459
tbxark/ChatGPT-Telegram-Workers TypeScript ai-agent 1K+ BENCHMARK

Easily deploy your Telegram ChatGPT bot on Cloudflare Workers (or Vercel, Docker...).

3,810 | 896 (23.5%) | 153
Ontos-AI/knowhere Python ai-agent 1K+ BENCHMARK

Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.

3,799 | 340 (8.9%) | 152
Ar9av/obsidian-wiki Python ai-agent 1K+ BENCHMARK

Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents

3,598 | 364 (10.1%) | 144
Snailclimb/interview-guide Java ai-agent 1K+ BENCHMARK

Spring Boot 4.1 Java 25 Spring AI 2.0 React PostgreSQL/pgvector Redis RustFS AI RAG

3,393 | 764 (22.5%) | 136
fuxicodex/Fuxi Python ai-agent 1K+ BENCHMARK

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

3,341 | 268 (8.0%) | 134
zeronsh/zeron Rust ai-agent 1K+ BENCHMARK

A native control plane for Claude Code, Codex, Cursor, Devin and other coding agents.

3,320 | 339 (10.2%) | 133
EvoMap/AutoResearch Python ai-agent 1K+ BENCHMARK

AI/ML research agents from idea to paper-ready evidence. An EvoMap open-source project.

3,177 | 287 (9.0%) | 130
HarnessRouter/harnessrouter Python ai-agent 1K+ BENCHMARK

HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.

3,158 | 347 (11.0%) | 127
MaxMiksa/Autonomous-Company Python ai-agent 1K+ BENCHMARK

An autonomous company working 24/7 on your own PC - Windows/Linux/macOS.

3,153 | 502 (15.9%) | 127
Natively-AI-assistant/natively-cluely-ai-assistant TypeScript ai-agent 1K+ BENCHMARK

Natively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Interview Coder. Real-time transcription, AI meeting notes, lecture recording, local RAG, BYOK, and stealth mode. Runs locally. No subscriptions. No data breaches.

3,036 | 639 (21.0%) | 122
Tiger3807861189/J-Space-Cognition-Suite Python ai-agent 1K+ BENCHMARK

J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.

2,970 | 238 (8.0%) | 119
cocoindex-io/cocoindex-code Python ai-agent 1K+ BENCHMARK

A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!

2,932 | 241 (8.2%) | 118
jeremylongshore/tons-of-skills-marketplace Python ai-agent 1K+ BENCHMARK

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

2,855 | 422 (14.8%) | 115
feitangyuan/onetake Python ai-agent 1K+ BENCHMARK

Motion films that never cut to the next slide: every beat grows out of the one before, one continuous camera, continuity measured by an oracle. Product launch films and feature demos, made with a coding agent.

2,778 | 223 (8.0%) | 112
Vincentwei1021/anything2explainer TypeScript ai-agent 1K+ BENCHMARK

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

2,644 | 356 (13.5%) | 106
org2AI/ORG2 TypeScript ai-agent 1K+ BENCHMARK

System of record for how agents build software: Built-in rust harness & 20+ CLIs.

2,630 | 211 (8.0%) | 106
Pinvou/pinvou-agent Rust ai-agent 1K+ BENCHMARK

Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

2,619 | 383 (14.6%) | 272
Zafer-Liu/Data-Analysis-Agent Python ai-agent 1K+ BENCHMARK

LLM-powered conversational data analysis agent that generates interactive visualizations and business insights without SQL.

2,611 | 228 (8.7%) | 105
aingdesk/AingDesk TypeScript ai-agent 1K+ BENCHMARK

AingDesk AI API AingDesk is a simple and easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, internet search, and intelligent agents. It is still growing rapidly.

2,541 | 294 (11.6%) | 102
yyjeqhc/webcodex Rust ai-agent 1K+ BENCHMARK

Give cloud AI agents a real development environment on your own machines.

2,375 | 320 (13.5%) | 95
moorcheh-ai/memanto Python ai-agent 1K+ BENCHMARK

Memory that AI Agents Love!

2,334 | 739 (31.7%) | 94
phronesis-io/eigenflux Go ai-agent 1K+ BENCHMARK

Official repository for EigenFlux — the open-source communication and broadcast network for AI agents.

2,226 | 179 (8.0%) | 90
coldteadotai/pr-lens TypeScript ai-agent 1K+ BENCHMARK

Review code 100X faster. Lens draws every PR as animated architecture and data-flow walkthroughs, inside the pull request itself. Use it as a GitHub App, GitHub Action, CLI, or a Skill for your coding agent

2,158 | 173 (8.0%) | 87
olaxbt/ai-market-maker Python ai-agent 1K+ BENCHMARK

Agentic AI Hedge Fund OS (AIMM)

2,115 | 303 (14.3%) | 220
zhimaAi/chatwiki Vue ai-agent 1K+ BENCHMARK

ChatWiki AI Agent RAG AI coze n8n

2,091 | 326 (15.6%) | 84
uber/ADR Python ai-agent 1K+ BENCHMARK

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

2,070 | 229 (11.1%) | 83
Jakeschincariol/youtube-agent-skill Python ai-agent 1K+ BENCHMARK

Eleven Claude skills that run a YouTube channel: scripts off 21 hook formulas with a scored hook, title and thumbnail linted as one pairing, an edit decision list from your transcript, a retention reader that finds where viewers actually leave, a Shorts cutter, and a virality engine. Free, MIT.

2,056 | 648 (31.5%) | 83
happier-dev/happier TypeScript ai-agent 1K+ BENCHMARK

Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity, Kimi, Augment Code, Qwen, fully end-to-end encrypted

2,015 | 192 (9.5%) | 81
team9ai/team9 TypeScript ai-agent 1K+ BENCHMARK

Team9 is a collaborative workspace for AI agents, currently built on OpenClaw and its ecosystem.

1,968 | 217 (11.0%) | 79
academa-labs/manimgx Python ai-agent 1K+ BENCHMARK

The animation engine for agents: blazingly fast math and 3D videos with Manim's Python API, on a Rust GPU core.

1,954 | 157 (8.0%) | 79
zchoi/Awesome-Embodied-Robotics-and-Agent TypeScript ai-agent 1K+ BENCHMARK

This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥

1,906 | 153 (8.0%) | 77
shiwenwen/hope-agent Rust ai-agent 1K+ BENCHMARK

🦭 A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment Agent AI NAS /

1,891 | 169 (8.9%) | 91
QVerisAI/QVerisFlow Python ai-agent 1K+ BENCHMARK

Automatic multi-agent workflow generation, fully integrated with QVeris unified data and tool layer

1,886 | 151 (8.0%) | 76
Core-Mate/OpenGUI HTML ai-agent 1K+ BENCHMARK

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

1,822 | 146 (8.0%) | 73
nano-muse/nanoMuse Swift ai-agent 1K+ BENCHMARK

nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.

1,777 | 198 (11.1%) | 72
TokenRhythm/NeoHorse Python ai-agent 1K+ BENCHMARK

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

1,742 | 140 (8.0%) | 70
croffasia/itsaplan TypeScript ai-agent 1K+ BENCHMARK

⭐️⭐️⭐️ Open-source, self-hosted alternative to Linear and Plane. Project management and issue tracking where teams and AI agents work side by side to plan and ship products.

1,647 | 233 (14.1%) | 66
ray-r-ren/agent-apprenticeship Python ai-agent 1K+ BENCHMARK

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

1,617 | 130 (8.0%) | 65
axoviq-ai/synthadoc Python ai-agent 1K+ BENCHMARK

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

1,592 | 159 (10.0%) | 1592
unitedbyai/droidclaw TypeScript ai-agent 1K+ BENCHMARK

turn old phones into ai agents - give it a goal in plain english. it reads the screen, thinks about what to do, taps and types via adb, and repeats until the job is done.

1,570 | 238 (15.2%) | 63
RLinf/RPent Python ai-agent 1K+ BENCHMARK

RPent: Agentic Infrastructure for the Physical World

1,568 | 139 (8.9%) | 63
imxv/Pretty-mermaid-skills JavaScript ai-agent 1K+ BENCHMARK

AI Agent Skill to generate and render beautiful Mermaid diagrams as SVG or terminal ASCII — 15 themes, 6 diagram types, batch CLI, no browser.

1,536 | 123 (8.0%) | 62
Continuum-AI-Corp/OrcaRouter-Lite Python ai-agent 1K+ BENCHMARK

Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter

1,523 | 265 (17.4%) | 140
ZJU-OmniAI/Data-Copilot Python ai-agent 1K+ BENCHMARK

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

1,512 | 153 (10.1%) | 61
HanyuanWang/LiveStream-Agent-Studio Python ai-agent 1K+ BENCHMARK

Autonomous Python AI agent and orchestration framework for LiveStream Agent Studio workflows.

1,502 | 187 (12.5%) | 141
iAmCorey/Wake Rust ai-agent 1K+ BENCHMARK

All your AI agent sessions in one place — browse, search, resume. Rust + GPUI.

1,481 | 119 (8.0%) | 60
Paritok-official/paritok-4b-v1 Python ai-agent 1K+ BENCHMARK

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

1,460 | 140 (9.6%) | 132
changexbc/workbuddy-switch Rust ai-agent 1K+ BENCHMARK

WorkBuddy CodeBuddy Token agent

1,440 | 182 (12.6%) | 58
ZJU-REAL/ClawGUI Python ai-agent 1K+ BENCHMARK

Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.

1,361 | 109 (8.0%) | 55
study8677/repobrain Python ai-agent 1K+ BENCHMARK

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

1,351 | 267 (19.8%) | 55
autonomous-ai/openharness TypeScript ai-agent 1K+ BENCHMARK

The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.

1,328 | 116 (8.7%) | 54
sipyourdrink-ltd/bernstein Python ai-agent 1K+ BENCHMARK

The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

1,314 | 184 (14.0%) | 1314
tigerowo/infinite-canvas TypeScript ai-agent 1K+ BENCHMARK

Autonomous TypeScript AI agent and orchestration framework for infinite canvas workflows.

1,262 | 271 (21.5%) | 51
heymrun/heym Python ai-agent 1K+ BENCHMARK

Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

1,228 | 99 (8.1%) | 1228
jieyefriic/rp-engine Rust ai-agent 1K+ BENCHMARK

YAML-native agent workflow execution engine, written in Rust

1,209 | 97 (8.0%) | 49
Morgensonne/EditDeck Python ai-agent 1K+ BENCHMARK

Automated video and media editing deck powered by multimodal LLM scene analysis.

1,201 | 97 (8.1%) | 49
momozi1996/momo-code TypeScript ai-agent 1K+ BENCHMARK

MOMO CODE — RSI *JEV*Pi --AI coding agent that evolves with you

1,190 | 96 (8.1%) | 48
Dpro-at/Tel-Agent Python ai-agent 1K+ BENCHMARK

AI phone assistant | open-source

1,146 | 227 (19.8%) | 46
RUC-NLPIR/ARPO Python ai-agent 1K+ BENCHMARK

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

1,137 | 91 (8.0%) | 46
Page 1 of 8 (433 indexed repositories)
12345678 Next →
Help & Engineering FAQ