1.NousResearch / hermes-agent
The agent that grows with you
+126,462 stars
from 133,039 · score 11.75
Trending repositories
Ranked by Attention Score: stars gained over the last 180 complete days
24 repositories by Attention Score · May 7, 2026 – Nov 2, 2026 (UTC)
2.headroomlabs-ai / headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
+76,987 stars
from 1,580 · score 11.25
3.asgeirtj / system_prompts_leaks
Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.
+31,532 stars
from 39,064 · score 10.36
4.BerriAI / litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
+17,203 stars
from 45,296 · score 9.75
5.hesreallyhim / awesome-claude-code
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC (no affiliation). A delectable showcase of top tier skills, ambidextrous agents, scintillating status lines, top notch developer tooling, and also we have plugins
+14,966 stars
from 42,082 · score 9.61
6.langchain-ai / langchain
The agent engineering platform.
+14,321 stars
from 134,518 · score 9.57
7.wshobson / agents
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
+7,698 stars
from 34,383 · score 8.95
8.davila7 / claude-code-templates
CLI tool for configuring and monitoring Claude Code
+6,583 stars
from 26,461 · score 8.79
9.Aider-AI / aider
aider is AI pair programming in your terminal
+6,136 stars
from 43,749 · score 8.72
10.LearningCircuit / local-deep-research
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
+3,749 stars
from 5,727 · score 8.23
11.kyegomez / OpenMythos
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
+3,070 stars
from 11,844 · score 8.03
12.The-PR-Agent / pr-agent
🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.
+2,902 stars
from 10,965 · score 7.97
13.Arize-ai / phoenix
AI Observability & Evaluation
+2,646 stars
from 9,449 · score 7.88
14.langchain-ai / open-swe
An Open-Source Asynchronous Coding Agent
+1,599 stars
from 9,562 · score 7.38
15.aden-hive / hive
Multi-Agent Harness for Production AI
+1,251 stars
from 9,880 · score 7.13
16.xonsh / xonsh
🐚 Python-powered shell. Full-featured, cross-platform and AI-friendly.
+425 stars
from 9,259 · score 6.05
17.utensils / mcp-nixos
MCP-NixOS - Model Context Protocol Server for NixOS resources
+252 stars
from 618 · score 5.53
18.leeguooooo / claude-code-usage-bar
Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode
+173 stars
from 214 · score 5.16
19.eli64s / readme-ai
README file generator, powered by AI.
+151 stars
from 2,855 · score 5.02
20.ypollak2 / llm-router
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
+99 stars
from 21 · score 4.61
21.congmnguyen / claude-code-wsl2-setup
Guides and scripts for Claude Code on WSL2: screenshot paste, Windows notifications, LSP, and statusline.
+42 stars
from 13 · score 3.76
22.xvary-research / claude-code-stock-analysis-skill
Claude Code stock analysis skill: SEC EDGAR + market data, /analyze /score /compare — free, local Python tools. By XVARY Research.
+14 stars
from 5 · score 2.71
23.aiqualitylab / ai-natural-language-tests
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)
+11 stars
from 16 · score 2.48
24.vdalhambra / financekit-mcp
Financial Market Intelligence MCP Server — stock quotes, technical analysis, crypto data, and portfolio insights for AI agents
+5 stars
from 4 · score 1.79