#llm

Multi-provider LLM router for Go — retries, fallbacks, and streaming across OpenAI, Anthropic, Gemini, and more

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

Slim SDK for Soothe plugins and shared contracts (events, wire, display, protocols)

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

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.

A coding-discipline spec for OpenAI's Codex CLI, enforced by native Codex hooks + a rule-hit telemetry loop. Turns an AGENTS.md the model drifts from into a system that holds. Independent of oh-my-codex.

Fast WebGPU runtime for 1-bit (binary-weight) LLMs in the browser. Bit-exact, zero runtime dependencies.

E2E testing where you write plain language and the LLM plans once — every replay is deterministic, LLM-free and costs $0.

A fast, lightweight candlestick chart library optimized for AI-driven applications and LLM integration

Adversary simulation and Red teaming platform with AI

A read-only, sanitized GitHub mirror of the open source release for @nhtio/adk

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

Synthia SDKs (npm + PyPI: synthiaresearch) and the synthia CLI — eval your AI agent against simulated users

Unified LLM client library for Go - one API, 36 providers (Anthropic, OpenAI, Google Gemini, AWS Bedrock, Mistral, Groq, DeepSeek, +29 more), zero external dependencies.

Hindsight memory plugin for OpenCode with Claude Code-aligned per-turn auto-recall

Go-native, zero-dependency LLM command-output compressor — an embeddable take on rtk (the Rust 'token killer') with lossless-by-default compression and credential redaction.

Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Drives IDA Pro, Roblox Studio, Wireshark, Blender, and any MCP server.

Local, project-scoped memory system for LLMs with evidence-based truth validation. Provides reliable long-term context via OpenAI-compatible Proxy and MCP, using Chain-of-Verification (CoVe) to eliminate hallucinations and the Ralph Loop for autonomous codebase repair.

Robust extraction of structured payloads from LLM output via sentinel blocks (<<<TAG>>> … <<<END>>>). Survives quotes, newlines & braces that break JSON.parse. 10 language ports, one spec.

Deterministic, evidence-based build harness for autonomous coding agents — FSM sprint gates, execution-evidence verification, and adversarial critics. Proof, not opinion.

Unified TypeScript AI client with Vercel AI Gateway defaults, provider escape hatches, model tiers, and normalized generation options.

Codebase intelligence shell and SDK — pip install jsat

Webbee Code 🐝 — the imperal.io Cloud coding ultra-agent in your terminal

Adaptive JSON-to-agent terminal output with exact token-aware format selection

Schedule, run, and track AI agents with zero infra.

A minimal, extensible agent library for Python.

Minimal, zero-dependency provider switching for Claude Code — switch between Anthropic, OpenRouter, DeepSeek, Z.AI, Kimi, Qwen, MiniMax and custom endpoints

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

The localhost AI Agent Runtime - Chat UI, Tools, RAG, and MCP in one pip install

A self-service AWS platform that lets developers create compliant CI/CD pipelines in minutes while platform teams enforce security, governance, and organizational standards.