Havuz

Gobstopper is an intelligent compaction proxy for Claude Code and Codex. It compacts more often, keeps history local, and cut tokens 29% on

CLI tool that turns natural language into shell commands via LLM

Lightweight, dependency-free logging and analytics for LLM API calls — track tokens, cost, and latency to a plain JSONL file.

Measurement for coding agents building UI: extract a contract from the reference page, check the implementation, get numbers back

Self-healing, config-as-code stack for the OpenCode AI coding agent — one key, 17 curated OpenRouter frontier models (GLM/DeepSeek/Gemini/Qw

Terminal-native AI assistant built specifically for Termux and Android development.

The AI agent with a memory that lives on your machine and answers the phone.

The networked cross-session for coding agents — @mention another team's AI so yours and theirs integrate directly across sessions, machines,

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-wi

Write commit messages, grep by meaning, turn English into shell — small composable CLI tools backed by an LLM. Local by default (no API key)

A plan-driven, multi-agent coding loop: separate planner, coder, and reviewer roles, each on the provider and model you choose, work togethe

Is your CLI ready for AI agents? Automated checks to ensure optimum agentic CLI use: don't block agents, don't waste tokens, ensure safe use

Your AI works the night shift — read-only reviews of your projects while you're busy, one digest every morning.

Offline-first project context and durable team management for coding agents. A local SQLite CLI for tasks, sessions, checkpoints, worktrees,

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then au

Vendor-neutral orchestrator that rotates a coding task across multiple AI coding agents

Shorter replies with Claude Code. Save output token spend.

Local terminal coding agent: CLI + TUI. Bring your own key/sub. Fork of oh-my-pi.

The most complete Dify MCP server + CLI — 193 tools for building, testing, and shipping Dify workflows, with Dify 1.18 support.

Voice agents in YAML, compiled to Pipecat or LiveKit. Production code you own, deployed anywhere.

A statistical code analyzer built from your repository's history.

A Codex CLI plugin that grades how you collaborate with Codex across 9 dimensions in 3 categories — your Codex model writes a free-form diag

Blue: a TUI is not a package, it is a Cordis plugin tree — a modern terminal UI for DeepSeek Harness with hot-swappable render, interaction,

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

Drive Google's Antigravity CLI (agy) from Claude Code: system-prompt sharing + a research-method prompt prefix. CLI counterpart to the IDE b

Turn noisy command output into a short, actionable first pass for coding agents.

Did your change make your LLM server faster? Measure it: faster, slower, or too close to call. Linux and Apple Silicon.

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Your AI coding agent just billed you. Here's the receipt. Cost receipts for Claude Code, Codex, Cursor, Gemini & opencode — no account, no u

Turn a YouTube video or a web article into didactic study notes, rendered as a self-contained HTML page. Agent skill for Claude Code, Codex,

Watch your Claude Code subagents work as a pixel-art office. Rewind any second, see what every agent cost, and turn any session into a timel

Use GitHub Copilot as a local OpenAI/Anthropic-compatible API for Codex CLI, Claude Code, and Continue.

Agentic AI development loop that splits Design, Code, Review, and Test into isolated roles with deterministic guardrails

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

Itemized cost receipts for Claude Code and Codex — by turn, verified, local.

CLI text optimizer built on GEPA. Uses Agentic Coding CLI's as mutator and observer -- no api keys required

One command to turn any codebase into an MCP server

User Interface for Prime-Agent

Paste a redacted copy of your clipboard with one hotkey. Hides API keys, tokens, passwords and PII (900+ patterns) before they reach AI chat

Free, open-source AI coding agent for terminal and browser. A Claude Code / Cursor alternative that runs offline with Ollama or with your ow

A team of AI agents that runs your job search — self-hosted, on your own LLM subscription. MIT.

为 Token 燃烧而生：token 越来越便宜，质量永远稀缺——与其省 token，不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优，用冗余换质量。Go 写的开源终端 Coding Agent，类 Claude Code，可接入任意模型，对团队友好

One hotkey to ask any AI on Mac. Open-source menu bar assistant: press ⌥Space to ask with your own API key (OpenAI, Claude, any OpenAI-compa

Local-first work memory for Claude Code, Codex and Copilot. Plain Markdown files hold your projects, people, decisions and meetings, with a

coding agent with user-approved SEA recursive self-evolution, ICM curiosity-driven evidence exploration, and bounded ToA multi-agent researc

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Met

An open-source DSL and compiler for floor plans: write .arch source (or have an AI agent write it) and compile it to SVG, DXF or PDF with li