#llm

Public TypeScript SDK and integration examples for Punk, the adaptive runtime for production AI agents.

Practical RouterBase examples for Node.js, Python, Docker, and modern TypeScript runtimes.

Local background agents on Claude Code and Codex CLI — they message each other, wake on demand, and share one memory.

JavaScript/TypeScript SDK for AI2Web: build the /ai2w manifest, serve the routes, and project to MCP, ACP, AP2, GraphQL & OpenAPI for AI agents.

An agent harness. Sandboxed tool suite, permission engine, context engineering with compaction and rewind, resumable sessions, per-turn cost, skills, subagents, MCP and web search. Works with OpenRouter or a ChatGPT Plus/Pro subscription.

AI-powered code convention checker for CI. Enforce your team's conventions from a plain-language YAML file — vendor-neutral, language-agnostic Go CLI.

An agent server. Agents, tools and models declared in files; every action checked against your policy before it runs. Any LLM, on your machine, Apache-2.0.

The SQLite of Vector Search & Episodic Memory for AI Agents in ~120KB. Pure C99, AVX2+FMA, ARM NEON, FASM x64, Native MCP Server.

该仓库未发布描述。

MCP server: the rail AI agents use to trade prediction markets. Self-hosted, non-custodial, on-chain builder-code attribution + overshoot & dispute-risk signals.

Claude Code (Anthropic) provider for the intisy-ai AI-proxy ecosystem.

Example reference provider for the intisy-ai AI-proxy ecosystem.

Create multi-agent workflows with AI and Language Models using OTP components in Elixir for reliable and scalable automation.

Validate API keys for OpenAI, Anthropic, Google Gemini, Groq, Mistral, OpenRouter, Cohere, DeepSeek, Together, Fireworks, xAI, and Perplexity. Zero dependencies. CLI + library.

Dense character notation for LLM-driven NPCs

该仓库未发布描述。

Fast LLM swapping with sleep/wake support, compatible with vllm, llama.cpp, etc. llama-swap fork.

Execution transparency for AI-written code: business-logic tracing that reads as a narrative. Redacted, diffable, approval-testable traces for humans and AI agents. NarrativeTrace for Java.

该仓库未发布描述。

macOS local-first chat & agent tool with interactive data analysis (Wails v2 + React)

Privacy-first CLI that transforms Jira tickets into AI-ready briefs. 60–80% fewer tokens. No relay. Pipe-friendly.

Smarter AI Development Workflows

Rysh CLI — agentic terminal multiplexer (open source)

Portable, cross-agent memory & workflow for AI coding agents — Claude Code, Codex, Cursor, Devin, and more. Monorepo: memory substrate, the kit (composition root), CLI bridges, and the engine.

该仓库未发布描述。

Provides building blocks to integrate with AI / LLM providers and built-in, common, providers.

SDK-free, zero-dependency Go wrapper for chat completions (with streaming) and embeddings across 18 LLM providers behind one unified, normalized surface.

A Model Context Protocol (MCP) server implementation that integrates with WebScraping.AI for web data extraction capabilities.

Self-hosted AI gateway. Route, translate and track requests across providers, with access keys, budgets, and a built-in dashboard.

Extension for the pi coding agent that intelligently routes each turn to the right LLM tier (high/medium/low) based on task intent, session budget, context size, and custom rules.