#developer-tools

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.

Air-traffic control for AI agents editing a shared repo - semantic pre-flight collision detection over MCP. Model-agnostic (Claude Code, Cursor, Codex).

MCP gateway for Codex to orchestrate external coding-agent harnesses, with normalized lifecycle, localhost settings UI, and fail-closed no-overage safety.

An agent composition framework that builds stacks and compiles specialized subagents for Claude Code

beecork — a tiny CLI coding agent built from scratch (TypeScript, OpenRouter)

Modular development framework with multi-vault secrets, Claude Code integration, extensible hooks, and health checks.

A modern, fast task runner for Rust projects.

Load test HTTP, database, and Redis on one clock and correlate their latency to pinpoint the real bottleneck — with a shareable HTML report

Replays your README and everything in docs/ inside a clean container, then checks every flag and command they cite against the real binary. Your docs tree rots faster than your front page, because nobody reads it on the way past. Verdicts, not a green tick. CLI and GitHub Action.

Local-first semantic governance for AI agents: contracts, impact, drift, evidence, and verified execution. Codex is the first native integration.

Switch between multiple Claude Code providers (Kimi, GLM, MiniMax, etc.) with a single command.

基于 Go AST 和类型信息，分析 Git revisions 间直接及间接受影响的 package。Find directly and transitively affected Go packages between Git revisions.

your todos herded

Your AI finds the open-source tool it needs on GitHub. Legwork installs it in a sandbox.

Pin feedback to the live UI. Hand it to Claude. An embeddable visual-feedback SDK — inspect an element, pin a comment, capture a screenshot; comments re-anchor across redeploys and reach Claude Code via MCP.

Parallel branching made simple. Create, switch, sync, and clean up worktrees in one CLI

Keep local project files without adding them to your main Git history.

High-performance Go tools for LLM Agents (MCP/CLI). 100x faster than Python. Includes native MCP Server, token-optimized search, and persistent project memory.

A coding-discipline spec for OpenAI's Codex CLI, enforced by native Codex hooks + a rule-hit telemetry loop. Turns an AGENTS.md the model drifts from into a system that holds. Independent of oh-my-codex.

The Git CLI that is safe to hand to your AI Agents: no sharp edges by design, commit concurrency built-in, Git-compatible because it uses Git plumbing under the hood

Low-noise Slack notifications for Claude Code that only fire when the agent is really done

AI Coding Gatekeeper — Zero-config, real-time guardrails for AI-generated code. 零配置AI编码守门员，实时拦截架构/安全/回归问题。

Autonomous agent ecosystem — CLI tools that provision, scaffold, and maintain Claude Code agent ecosystems

Verifiable coding-agent harness in Go: external test gates, typed outcomes, sandboxed execution, multi-model providers, and signed proof bundles.

Stop your AI coding agent breaking things. Enforced guardrails that block unsafe edits, composable modes, and token-cost budgeting for Kiro CLI.

Decisions that can't silently rot — anchor a design decision to the exact code it governs, follow it through refactors and renames, and fail CI when the code changes but the rationale doesn't.

A simple immutable dictionary for Python

Terminal dashboard for Claude Code, zero config, track all sessions, switch context instantly, never lose track of what's running

Profile where Claude Code tokens actually go: a single Go binary that reads a session JSONL and prints a flame-graph-style tree of system / skill / mcp / file / reasoning / output, reconciled to real per-turn usage, plus an allocation_v1.json schema.

A TUI for previewing your PR as the code agent builds it. Provides simple copy/paste context for your LLM when you need to make changes. Pronounced "review-ee"