llm-agents-radar

Live-updating index of LLM agent frameworks shipping on GitHub, refreshed every 15 minutes
**⭐ Star this repo to bookmark — fresh data every 15 minutes**
English · 中文 · 日本語 · 한국어 · Español · Português
---
💡 What is this?
A self-updating tracker that discovers and indexes new LLM agent frameworks as they appear on GitHub. Unlike static awesome-lists that go stale within weeks, this project uses GitHub Actions to continuously scan for new repos, rank them by activity signals, and publish a structured feed developers can query or browse.
This list is **auto-updated every 15 minutes** by a GitHub Actions cron.
Each commit reflects a real change in the upstream data source — new items added,
expired items removed — so you can rely on what you see being current.
---
📋 Current Items
> ⏰ Last updated: 2026-10-16 07:45 UTC
>
> Data source: GitHub Search API
>
> The table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|------|---|------|---------|-------------|
| 1 | uukuguy/capstone | 0 | Python | 2026-10-16 | Capability-first framework for evidence-backed applications over authoritative business-domain systems. First applicatio |
| 2 | Chensihakniroth/anakot-agent-v1 | 0 | Python | 2026-10-16 | Lean, extended fork of Nous Research's Hermes Agent — free model suite, connectors, and ~20 perf fixes. Upstream credite |
| 3 | ongridio/ongrid | 1186 | Go | 2026-10-16 | An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, L |
| 4 | tomcounsell/ai | 29 | Python | 2026-10-16 | A productive AI coworker that learns, self-improves, and ships work. |
| 5 | Shuffle-1992/dsh-context-pilot | 2 | JavaScript | 2026-10-16 | DSH 上下文智能压缩 + 智能思考：每轮注入用量、模型自主决定压缩并自动续跑；可选让模型按任务难度自主调整思考强度档位 |
| 6 | ljedrz/nachalnik | 5 | Rust | 2026-10-16 | A transparent agent runtime in Rust: context, tools, permissions and requests as explicit state. Plus an MCP bridge and |
| 7 | protoLabsAI/protoAgent | 13 | Python | 2026-10-16 | Local-first agent that drives Claude Code and Codex over ACP. Desktop app, git-URL plugins, A2A 1.0. MIT. |
| 8 | dsswift/ion | 4 | TypeScript | 2026-10-16 | Headless multi-provider LLM agent runtime. Single Go binary, 14+ providers, 70+ extension hooks, zero opinions. |
| 9 | plurnk/plurnk-service | 1 | TypeScript | 2026-10-16 | Plurnk engine: an operation language, searchable resources, persistent context, and cooperating workers. |
| 10 | denn-gubsky/loomcycle | 14 | Go | 2026-10-16 | The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sand |
| 11 | Aolin-MIR/triceratops-music-agent | 1 | Python | 2026-10-16 | Music Agent VST3 for REAPER: editable MIDI generation, continuation, audio-to-MIDI and stem separation. Native Windows. |
| 12 | aiterrariumcontrol/terrarium-life | 0 | Python | 2026-10-16 | The life record of an autonomous AI agent — its diary, work journal, and every wake it has taken. The observation window |
| 13 | xianyu-sheng/Xenon | 53 | Python | 2026-10-16 | Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checkli |
| 14 | anchor-inference/daedalus | 2 | Python | 2026-10-16 | A personal, self-developing AI agent you run yourself: its own app window on macOS, Linux and Windows, a web app on your |
| 15 | g761007/daily-dispatch | 0 | Python | 2026-10-16 | 每日新聞自動分析與摘要系統：Claude Code 雲端排程（routines）定時分析、彙整成每日摘要，透過 GitHub Pages 公開發布並用 Telegram 推播。 |
| 16 | zhixuli0406/DuDuClaw | 49 | Rust | 2026-10-16 | Turn AI coding CLIs (Claude Code, Codex, Antigravity) into AI employees on LINE, Telegram, Discord, Slack and 7 more cha |
| 17 | ZekaiShi/evo-subagent | 7 | JavaScript | 2026-10-16 | Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/ |