🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.
Repository Index
47,133 repositories indexed
121–144 of 153 · Most stars
Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies
- autoresearch
- claude-code
- cli
- developer-tools
Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.
Risk-adaptive development pipeline with adversarial consensus code review
Claude Code dashboard: see where your limits are headed before you hit them. Calibrated usage forecasts, live rate-limit gauges, session costs, memory browser. Single binary, zero config, plus a VS Code extension.
Neovim plugin for automaticaly passing extra context for LLM on code snippet copy to clipboard
It falls out of your notch. Hotkey, repo, Return: your terminal opens with Claude Code, Codex or any agent already running. Free, MIT, local-only macOS.
🔮 MAGUS Council: World's first? 4-AI consultation system (Gemini+Claude+GPT-5+Qwen) in VS Code - Revolutionary multi-agent development environment
Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI workflow.
Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and before/after composites, one command each. Self-contained Chromium, self-validated output, no MCP.
- annotation
- claude-code-plugin
- demo-recording
- screenshot
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.
- claude-code
- claude-code-plugins
- decision-tracking
- embeddings
🦫 Privacy-first virtualization layer for LLM context with MCP protocol for tool access.
The open-source map of the AI developer tooling ecosystem
See where it leaks, stop paying for it — a live Claude Code status line that prices every turn, your subagents, cache rebuilds, plus limits, context and git.
Persistent AI workflows for Neovim. OpenAI Codex and xAI Grok integration for Neovim with persistent sessions, workspaces and token monitoring.
Native macOS app for tracking Claude Code usage — tokens, cost, rate-limit pacing, per-project breakdowns. SwiftUI + SwiftData.
Minimalist command based AI plugin to interact with LLM backends like Ollama and OpenAI with a powerful template system
Neovim completion for local agent commands and skills, with env-gated Claude/Codex editor integration
- blink-cmp
- claude-code
- codex
- completion
Package manager for MCP servers, Agent Skills (SKILL.md), and Claude Code commands, hooks, subagents, and output styles. Installs into Claude Code, Cursor, Codex, Gemini CLI, Copilot, and Cline.
The prettiest statusline for Claude Code — pure bash, never blocks your prompt. Usage quota, context window, git status & more.
Decentralized agent memory for the Lightning economy. Nostr identity, L402 payments, MCP server.
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
Run agentic TUIs inside Neovim with persistent float/panel views and editor-context helpers.
- agentic-ai
- agentic-workflow
- agents
- claude
HTTP honeypot on autopilot
- canarytokens
- deception
- deception-technology
- honeypot