GitStar / GitHub Social Proof

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 (432)
agent-tower/core TypeScript ai-agent VIABLE (250+)

The command center for AI agents such as Claude Code, Codex, and Gemini-Cli, making your agents ten times more efficient.

391 32 (8.2%) 19
d-dev0101/open-sea-skin JavaScript ai-agent VIABLE (250+)

WebGPU ocean skin for DeepSeek Harness — DSH plugin, Harness-only Chrome/Edge extension, static installer, and native integration.

391 32 (8.2%) 16
Johnsheng1/cf-ai-TGbot JavaScript ai-agent VIABLE (250+)

CF-ai-TGbot is a customizable Telegram bot powered by Node.js, integrating Cloudflare AI Gateway for smart, context-aware conversations. 🌐🤖

386 31 (8.0%) 16
pax-beehive/dsh-hub-cli TypeScript ai-agent VIABLE (250+)

Open-source CLI, schemas, resolver, and DSH agent tools for DSH Plugin Hub

386 31 (8.0%) 16
useagenthq/useagent TypeScript ai-agent VIABLE (250+)

The open-source Devin alternative. Run Claude Code, Codex or OpenCode in isolated cloud workspaces you can self-host.

371 97 (26.1%) 15
Lincb522/GitGatto Swift ai-agent VIABLE (250+)

Autonomous Swift AI agent and orchestration framework for GitGatto workflows.

361 29 (8.0%) 361
shuyicc/MathLens Python ai-agent VIABLE (250+)

MathLens Agent Skill Manim 1-10 0.2-1

360 29 (8.1%) 19
KlaatAI/klaatcode TypeScript ai-agent VIABLE (250+)

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.

359 136 (37.9%) 17
AgenticMatrix/coderix TypeScript ai-agent VIABLE (250+)

A pure open-source coding agent developed by AI

357 31 (8.7%) 15
Sayhi-bzb/Agent-HTML TypeScript ai-agent VIABLE (250+)

You don't need a chat ui but a canvas with ai.

354 29 (8.2%) 15
OyadotAI/oya-browser TypeScript ai-agent VIABLE (250+)

The browser control plane for AI agents. One API over Oya Cloud, Browserbase, Steel, Anchor, Browser Use and your own Chrome, with persistent personas, CAPTCHA and MFA handling, and live human takeover.

351 279 (79.5%) 351
clay-good/OpenLore TypeScript ai-agent VIABLE (250+)

Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.

350 49 (14.0%) 14
pleaseai/shunt Rust ai-agent VIABLE (250+)

Shunt Claude Code agents to any model — selective, per-agent inference-layer routing proxy

340 28 (8.2%) 14
skilltraining-project/skill-training Python ai-agent VIABLE (250+)

Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights.

339 28 (8.3%) 339
cqzyys/lang-agent TypeScript ai-agent VIABLE (250+)

LangChain LangGraph AI Agent

338 76 (22.5%) 29
feichai0017/orbitkv Python ai-agent VIABLE (250+)

High Performance KV Cache for LLM Inference

337 27 (8.0%) 337
chengrouter/chengos Shell ai-agent VIABLE (250+)

ChengOS is a visual AI data processing and agent workflow system. This directory contains deployment scripts, infrastructure configs, and runtime resources for production and development.

335 27 (8.1%) 335
ai-sns/ai-sns JavaScript ai-agent VIABLE (250+)

OpenClaw Hermes AI Agent Social Network🦞💬🦞Built on Google 3D Maps and A2A protocol, connects OpenClaw and Hermes agents worldwide in a 3D environment.

333 27 (8.1%) 14
AbubakrChan/product-launch-motion JavaScript ai-agent VIABLE (250+)

Claude Code skill for Dribbble-level product launch videos from code. One shape that never cuts, springs, a cursor that drives every change, beat-synced SFX, 60 fps motion blur. v2: use with Claude Opus 5.5.

332 49 (14.8%) 14
Danceiny/gotry TypeScript ai-agent VIABLE (250+)

Autonomous TypeScript AI agent and orchestration framework for gotry workflows.

332 27 (8.1%) 14
0xranx/golembot TypeScript ai-agent VIABLE (250+)

Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat — with any LLM provider.

323 45 (13.9%) 13
Xueyang-Song/paper-pilot TypeScript ai-agent VIABLE (250+)

Research-paper workflow tool for literature triage and structured reading

311 39 (12.5%) 24
YutoTerashima/agent-safety-eval-lab Python ai-agent VIABLE (250+)

Agent trace and tool-use safety evaluation lab.

309 25 (8.1%) 13
zhangweijp/AgentOrientedTUI TypeScript ai-agent VIABLE (250+)

Building Software for AI Agent.

309 25 (8.1%) 13
tinyhumansai/opencompany Rust ai-agent VIABLE (250+)

Run a hive mind of agents to focus on a specific goal

308 59 (19.2%) 13
ad-naan/Adnify TypeScript ai-agent VIABLE (250+)

A local‑first AI Agent IDE that plans, edits, debugs and ships projects. Your clever otter‑flavored coding teammate.🦦

306 51 (16.7%) 13
ATaC-team/ATaC TypeScript ai-agent VIABLE (250+)

Record and Replay AI Agent Trajectories.

302 25 (8.3%) 13
ybuild-ai/ai-game-art-pipeline-skill Python ai-agent VIABLE (250+)

Agent skill from Y Build for turning AI images and videos into playable game art assets

301 25 (8.3%) 13
Simreal-AI/Simreal-MLBench Python ai-agent VIABLE (250+)

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.

300 39 (13.0%) 30
realmyang/MLView Python ai-agent VIABLE (250+)

Interactive, source-linked ML workflow diagrams written by your coding assistant (Copilot, Codex or Claude Code) and opened in VS Code.

296 26 (8.8%) 16
SakanaAI/mass Python ai-agent VIABLE (250+)

Multi-Agent Self-Supervision

293 30 (10.2%) 12
JetXu-LLM/llama-github Python ai-agent VIABLE (250+)

Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Solutions to conduct Agentic RAG from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.

291 24 (8.2%) 16
jarrycyx/openlens-ai Python ai-agent VIABLE (250+)

OpenLens AI A Fully Autonomous Multimodal Research Agent OpenLens AI

282 28 (9.9%) 12
YangXuanyi/Multi-Agent-GPT Python ai-agent VIABLE (250+)

Multi-Agent-GPT RAG agent GPT

272 22 (8.1%) 11
zengzag/WorkAvatar TypeScript ai-agent VIABLE (250+)

A desktop app for autonomous AI digital employees — with an offline-first local knowledge base and an extensible plugin ecosystem.

266 22 (8.3%) 266
mangopy/direct-rag-learning Python ai-agent VIABLE (250+)

Official code for TOIS2026 "Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models"

264 22 (8.3%) 11
harnessclaw/harnessclaw TypeScript ai-agent VIABLE (250+)

Harnessclaw is a powerful, Electron-based desktop application designed to manage, chat with, and operate AI agents and skills seamlessly.

264 54 (20.5%) 264
69gg/Undefined Python ai-agent VIABLE (250+)

QQ bot platform with cognitive memory architecture and multi-agent Skills, via OneBot V11.

262 21 (8.0%) 11
sunreview/GetClaudePro TypeScript ai-agent VIABLE (250+)

Claude Pro + Organization ID How to subscribe to Claude Pro without an international card step-by-step guide Как оплатить подписку Claude Pro без зарубежной карты пошаговое руководство

260 21 (8.1%) 11
Ariestar/sivtr Rust ai-agent VIABLE (250+)

A unified agent memory workspace for human and agent agent

257 22 (8.6%) 11
FreeAccHub/qaa-airtype Python ai-agent VIABLE (250+)

Autonomous Python AI agent and orchestration framework for qaa airtype workflows.

254 21 (8.3%) 11
pqpo/pragma TypeScript ai-agent VIABLE (250+)

Build portable agent teams across models and harnesses, with shared memory, skills, tools, and workflows then bring them into Codex, Claude Code, or any AI system you build. harness Agent Team Codex Claude Code AI

252 21 (8.3%) 11
franzvill/lad Python ai-agent VIABLE (250+)

An open protocol for discovering A2A-capable AI agents on local networks — the discovery & trust bootstrap layer beneath A2A (mDNS/DNS-SD, well-known endpoints, signed AgentCards).

250 31 (12.4%) 35
suitedaces/dorabot TypeScript ai-agent -4 TO 250 FLOOR

macOS app for 24/7 AI agents in an IDE with memory, scheduled tasks, browser use + access to Whatsapp, Telegram, Slack.

246 37 (15.0%) 12
AIFrontierLab/AgentArk Python ai-agent -6 TO 250 FLOOR

[NeurIPS'26] Official Implementation for AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent(https://arxiv.org/abs/2602.03955)

244 30 (12.3%) 20
FrankHui/paragents Python ai-agent -11 TO 250 FLOOR

Parallel ai-agent sessions in one panel, with permission-aware tools, preflight conflict checks.

239 20 (8.4%) 239
WLXie-Tony/Movie_Review_Analysis Jupyter Notebook ai-agent -12 TO 250 FLOOR

Official replication package for IJFE (2026). Asynchronous ETL pipeline using GPT-4o to quantify investor distraction shocks from unstructured movie reviews.

238 20 (8.4%) 10
zht475706171/TaiSang Python ai-agent -20 TO 250 FLOOR

Autonomous Python AI agent and orchestration framework for TaiSang workflows.

230 19 (8.3%) 230
Cellium-Project/Cellium-Agent Python ai-agent -24 TO 250 FLOOR

AI Self-Evolving AI Agent Framework Decision-Loop Driven Microkernel Architecture with Hot-Pluggable Components & Triple-Layer Memory Agent Infinite Evolution Engine that Learns from Failures

226 19 (8.4%) 226
Francis206/wazuh-ai-soc-azure Python ai-agent -24 TO 250 FLOOR

wazuh azure security-operations siem mistral llm hipaa terraform aks mlops soc open-source azure-api-management lora fine-tuning

226 20 (8.8%) 10
kirincolor/openmesh Python ai-agent -26 TO 250 FLOOR

A local, multi-agent workspace designed like a messenger-style app. You can add custom teammates and chat with them individually, or create group chats and choose exactly which teammates to include. The whole experience feels like a familiar messaging app—but with much more powerful multi-agent collaboration capabilities.

224 23 (10.3%) 9
moskoo/xxg-portrait-rebuild-light Python ai-agent -32 TO 250 FLOOR

`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and background atmosphere with a director-led lighting workflow while restoring clean, healthy, low-contrast photographic skin microtexture.

218 24 (11.0%) 14
petershifi123-wq/solve-lite Python ai-agent -32 TO 250 FLOOR

CoreML-native local decision runtime for AI agents · 18 install profiles · 20-scenario protocol · offline · ~50.93 MB · by Soulite Magic

218 18 (8.3%) 218
healer-666/Academic-Data-Agent Python ai-agent -34 TO 250 FLOOR

Academic-Data-Agent is a research-oriented agent system for structured tabular data.

216 18 (8.3%) 9
shizhl/CoAgents Python ai-agent -36 TO 250 FLOOR

Official code for paper "Learning to Use Tools via Cooperative and Interactive Agents"

214 18 (8.4%) 9
skyler-he/komari-agent-docker Dockerfile ai-agent -37 TO 250 FLOOR

Autonomous Dockerfile AI agent and orchestration framework for komari agent docker workflows.

213 18 (8.5%) 9
matrixarkai/TemporalStore Rust ai-agent -38 TO 250 FLOOR

Open-source Rust TemporalStore for LLM context management, temporal features, and risk control

212 44 (20.8%) 29
Wholiver/swiftui-design-skill TypeScript ai-agent -40 TO 250 FLOOR

SwiftUI Front-End Design Skills — Six Ironclad Rules Against AI Sloppiness, Design Direction Consulting, Brand Asset Guidelines, and Five-Dimensional Review. Supports all AI agent platforms, including Claude Code, Cursor, Codex, and OpenCode.

210 17 (8.1%) 15
Javis603/Discord-AIBot JavaScript ai-agent -43 TO 250 FLOOR

🤖 Discord AI assistant with OpenAI, Gemini, Claude & DeepSeek integration, multilingual support, multimodal chat, image generation, web search, and deep thinking

207 17 (8.2%) 9
kkw114514-lang/campus-job-application-workflow Python ai-agent -45 TO 250 FLOOR

AI / / / / An AI-driven campus recruitment application workflow with a generic, privacy-safe template.

205 17 (8.3%) 205
Page 3 of 8 (432 indexed repositories)
← Previous 12345678 Next →
Help & Engineering FAQ