A live, local-first dashboard for Claude Code sessions: project graph of agents, tokens, tool feed, replay, alerts. Plugin + terminal UI + MCP server. Includes the AOS-1 agent orchestration spec.
Source
GitHub
Language
JavaScript
Last activity
Oct 23, 2026
Stars76Measured · Oct 25, 2026
Momentum62.67 days · Measured · +40.74% relative change
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
Source
GitHub
Language
TypeScript
Last activity
Oct 24, 2026
Stars1,776Measured · Oct 25, 2026
Momentum62.57 days · Measured · +6.41% relative change
Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the job and the reflexes to not break your repo. For Claude Code, Codex and 15 more.
Source
GitHub
Language
JavaScript
Last activity
Oct 23, 2026
Stars270Measured · Oct 25, 2026
Momentum62.57 days · Measured · +18.94% relative change
Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent). Task-based model routing, cross-model code review, new-model alerts. Saves tokens and quota; the host verifies every diff.
Source
GitHub
Language
Python
Last activity
Sep 30, 2026
Stars14Measured · Oct 25, 2026
Momentum62.27 days · Measured · +180% relative change
A lightweight pre-coding check for Codex, Claude, Cursor, Antigravity, Gemini, and Grok: look up what you can, and ask only when an unresolved choice would change the result.
Source
GitHub
Last activity
Oct 24, 2026
Stars9Measured · Oct 25, 2026
Momentum62.27 days · Measured · 0% relative change