#llm

A tiny, fast Rust CLI that drives a real browser over the Chrome DevTools Protocol — built for coding agents.

Keine Repository-Beschreibung veröffentlicht.

Cut ~90% of Claude Code's context usage while keeping nearly all the memory

Policy-aware model execution with portable routing, budgets, fallbacks, and receipts

Local Tokenizer/Counter

Production observability for MCP servers. Traces, metrics, and logs — wired up in two lines.

LLMs as Copilots for Theorem Proving in Lean

Go agent knowledge library for CLIs — embedded guides, schema introspection, and skill export

AI venture studio: mines your support tickets and issues for opportunities, sizes markets honestly, writes PRDs with kill criteria, builds and reviews the product from one plain-language doc (English/中文), measures real cohorts, and forces honest kill decisions. Humans hold every gate; it never publishes or spends.

"Unit tests" for your agent skills

verification toolchain for TypeScript (Tech Preview)

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

💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.

A fully functional and production-ready agent that could be embedded in your applications.

Agent Tool Protocol

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

AISEF — AI Software Engineering Framework: one requirements file in, a gated and evidence-backed application out. Agents do the judgement; code enforces the guarantees.

Turn Codex into a full-scale ACP server. Zero deps. No OpenAI API keys. Uses your existing Codex subscription.

ACP-backed Google ADK agent adapter for Go

Soma makes AI agents trustworthy by providing observably traceable governance, evidence-based rule selection W/ JIT, AST analysis tools, TTC Verifiers, and adaptive rule lifecycle management.

A Laravel package for implementing secure Model Context Protocol servers using Streamable HTTP and SSE transport, providing real-time communication and a scalable tool system for enterprise environments.

CLI tool for bundling project files as LLM context.

A math AI assistant agent

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

Generative-AI abstraction (LLM, agents, image/audio/video)

milk — a CLI/TUI that routes prompts between agents: a primary agent and a configurable escalation agent, with session-aware state management and real-time streaming. Escalation happens automatically (via routing rules) or manually, preserving context across the handoff between agents.

Long-horizon AI harness you actually own: one static Go binary, one persona, any OpenAI-compat LLM (Ollama, Gemini, Claude, ChatGPT), MCP tools, chat via Telegram/Discord/Slack. Outbound-only — no dashboard, no config UI, no open ports, ever. Hardened so small local models finish tool calls.

Universal AI router — save 20-40% tokens with RTK and never stop coding. Connect Claude Code, Cursor, Antigravity, Kiro, Copilot, Codex, Cline & any OpenAI-compatible client to 40+ providers & 100+ models via one local endpoint. Zenith sub-1ms failover, MITM, multi-account.

Zero-dep streaming markdown for the browser — Rust→WASM, 100% CommonMark 0.31 + GFM. Built to not melt the main thread on concurrent LLM streams.

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