#anthropic

Tokenless is a deterministic OpenAI / Anthropic compatible mock gateway for testing agents without API calls, token costs, or unpredictable model responses

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.

OpenCode Plugin for supervised agentic software development on a Kanban board

该仓库未发布描述。

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

Local Tokenizer/Counter

Free AI inference router for developers - 21 providers, OpenAI-compatible

Hazzel — a small terminal coding agent that works on your code

A pure-Rust LLM API translation layer — one OpenAI-shaped request, routed and translated to OpenAI, Anthropic, Gemini, and xAI.

Provider-agnostic AI SDK for Go — unified interface for building AI agents across LLM providers

Production ready MCP server with real-time search, extract, map & crawl.

The full-stack open-source agentic ecosystem.

Keep your Claude Code / Codex 5h rate-limit windows back-to-back — auto-pings each provider the moment its window resets. | 在 5 小时限额窗口重置的瞬间自动触发计时,让 Claude Code / Codex 的窗口背靠背、不留空档。

该仓库未发布描述。

🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.

Lightweight Claude Code UI wrapper - integrates with your local settings and chats

Lightweight prompt injection detection for LLM applications

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

Cost dashboards tell you what your AI stack spent. Cage tells you what each tool actually saved you — and what a human would have cost instead.

GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

abide — type-safe isomorphic framework on Bun + web standards

Persistent memory for Claude Code, Cursor, Copilot & Windsurf — your AI stops re-reading your codebase every morning. 120+ MCP tools, semantic search, shared Team Brain. Free tier, EU-hosted.

AI-powered release notes for semantic-release

Hand a live Claude Code, Codex, or opencode session to anyone with three spoken words - encrypted, no account. Or carry your whole Claude Code history to a new laptop, every path rewritten.

Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. Inspired by docker-compose.

Save your Cursor monthly quota! Unlimited AI interactions in one conversation via MCP feedback loop.

Chainable reverse proxy with bounded concurrency for AI/LLM API endpoints. Limits concurrent requests, retries on failure, optional TUI dashboard.

ThunderAI is a Thunderbird Addon that uses the capabilities of ChatGPT, Gemini, Claude or Ollama to enhance email management.

An Elixir SDK for Claude Code - provides programmatic access to Claude Code CLI with streaming message processing

Vibe Codr — a local-first coding agent for desktop and terminal, with planning, subagent orchestration, memory, Git review, and any-model support.