#openrouter

Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.

🦅 Open-source AI agent runtime in Rust — Self-hostable with persistent memory, self-improving skills, MCP support, built-in cron, multi-platform messaging & production gateway.

Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog

My Claude Code (MCC) is a local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode, Gemini CLI and other AI coding agents — 57 providers, fallback routing, credential health, a native web-search tool proxy, and exhaustive analytics with cost provenance in one local dashboard.

CLI coding agent สไตล์ Claude Code — Claude API / Cloud / Ollama / llama.cpp, 42 skills, single-file

SillyTavern extension: one line (or nothing) → a complete, linked roleplay: card, openings, lorebook, preset, regex, Quick Replies, plus ComfyUI portraits and expression sprites. Hands-free AI with undo, provenance and a full creator's workbench.

Personal fork of free-claude-code: a Chrome side panel for the proxy, credential pooling, measured context windows, and a curated model list

Summon any AI from any CLI — a tiny, dependency-free cross-vendor sub-agent dispatcher (Claude, Codex, Cursor, Gemini, Antigravity + any OpenAI-compatible API). Council mode, fan-out swarms, structured JSON envelope.

🏆 Ultralight AI Coding Agent 2026 — Blazing CLI, Tiny Codebase, Full Power Free

Free AI coding assistant for VS Code & Cursor — Claude, GPT-4, Gemini & 300+ models. No subscription.

Local Jeopardy! for parties — LLM judges spoken answers, no host needs to know.

Claudy lets you switch between Anthropic, Z.AI, OpenRouter, Ollama, and custom endpoints with a single command — keeping credentials, config modes, and Claude frameworks cleanly isolated per profile. Multi-provider · Config isolation · Channel bridge · Local agent bridge · Usage analytics

Agent personnel autonome en Rust, tournant sans écran sur un Mac. Telegram ou SSH, mémoire en Markdown, serveurs MCP, workflows durables, approbation avant tout ce qui engage.

Local-first AI gateway. One OpenAI-compatible endpoint, 16 providers, free-first smart routing with automatic fallback. Every routing decision is stored and explained.

Local multi-protocol LLM API tester for OpenAI-compatible, Anthropic & Gemini endpoints · 本地多协议 API 测活工具

Système multi-agents LangGraph + FastAPI : routage chat/pipeline automatique, RAG Qdrant, MCP Brave Search, streaming WebSocket Redis, interface Next.js 14 et 78 tests

Profile-driven daily news agent: deterministic RSS collection + DeepSeek (OpenRouter) analysis, delivered to Telegram

How much prepaid credit is left at each of your LLM API providers — one static Go binary, 19 providers, no stored keys.

Cloud-based RAG chatbot built with Azure, FastAPI, Streamlit, ChromaDB, PostgreSQL, Docker, Terraform, and GitHub Actions.

Your tasks with 99% accuracy using any LLM (Claude, DeepSeek, Codex, Gemini, Hermes, OpenClaw, Cursor).

?? The World's First AI Blueprint Architect - Turn any wish into production-ready blueprints with multi-agent AI. Built with Next.js 16, React 19, TypeScript, Prisma & Vercel AI SDK.

Context-aware skill selection for AI agents — solves the 'too many skills' problem. Reduces skill context tokens by 85-98%, improves selection accuracy, learns from feedback.

Monk LLM Gateway: one API in front of every model. An LLM gateway and router built from scratch (proxy, routing, retry/fallback, caching, budgets), with an interactive course.

🖥️ Self-host build (single SQLite file, one process) of Liberde — an open-source Claude.ai for every model via OpenRouter: artifacts, design studio, web search, MCP + custom tools. Hosted version → liberde / liberde.ai.

Add ChatGPT-style deep research to your agent or product. Self-hosted multi-agent research API with async jobs, signed webhooks, SSE streaming, MCP server, and 7 LLM providers.

Open-source AI API client & LLM playground | Compare models, tokens & costs | 多模型 API 管理与对比平台

Daily 0-100 macro tailwind/headwind index per asset from the economic calendar, RSS news and LLM-extracted institutional forecasts. Python, SQLite, LiteLLM.

Track 440+ AI model costs and 32+ coding agent plans. Translates obscure tokens/credits into definitive usage metrics, benchmarks, and TOS gotchas.

Any coding agent. Any model. One command. Run Claude Code, Codex, OpenCode, Droid, Pi and more against OpenRouter, DeepSeek, Groq, Ollama or any OpenAI/Anthropic-compatible endpoint.

OpenAI-compatible LLM proxy that races multiple providers in parallel and returns the fastest usable answer. Cut token cost, slash latency, handle flaky free/local model tiers. Bring your own keys, no markup. Zero-dependency install on macOS & Linux (Apple Silicon, ARM64 SBCs).

An AI-powered YouTube Q&A system that lets users chat with video content using RAG pipelines, LangChain, FastAPI, and vector search.

Empirical study: do LLM-generated features improve tabular ML models? 10 LLMs, 3 datasets, 3 algorithms, 219 experiments.

This is a starter template for projects using Claude Code. It includes configuration files and guidelines to help you get started quickly.

AI-powered VK bot for beauty salons: booking, DB-backed pricing, OpenRouter LLM, admin handoff. Python, VKBottle, SQLAlchemy.

Boost LLM reliability with dynamic sampling, retry logic, and a lightweight Go‑based proxy.

AI support desk that routes complaints, drafts cited replies with hybrid RAG, and learns from every resolved case.

Conversational AI assistant built with Python, Gradio and OpenRouter API.

An AI-powered multi-agent system for analyzing, validating, prioritizing, and managing municipal infrastructure reports.

A free, privacy-first AI chatbot you run with your own OpenRouter key. No account, no server, no tracking — just chat. 🐾

Test-drive new LLMs as they drop — model-agnostic chatbot + 8-role coding multi-agent team on LangChain/LangGraph via OpenRouter (currently stealth/ox-alpha)