#llm

Unlimited Blade — an interactive coding agent TUI in Go, built for transparent, hands-on software development.

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

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

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

No repository description published.

Composer plugin that automatically discovers AI Mate extensions on install/update

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

Your agent forgets; nem doesn't. mnemonics encodes a session's decisions, edge-cases and facts into immutable, recallable structure — versioning agent context the way git versions code, shared across Claude & Codex.

Open, generic LLM-driven Extractor for herrscher: distills journal+transcript into memory candidates (facts + skills).

Herrscher — Obsidian memory plugin: a co-edited markdown knowledge graph (Project/Architecture/Production/Session/Decision/User nodes) implementing the contracts.Memory port.

An open source local-first terminal coding agent. Peer programming with any frontier model or local/free models to run agentic development.

A lightweight and elegant AI Agent framework

No repository description published.

No repository description published.

Deterministic, LLM-agnostic scaffolding CLI with adapters for Claude Code and GitHub Copilot CLI. Generates boilerplate code while letting AI agents focus only on business logic.

AI agent debugging, collaboration, and trace observability. Built for teams using CrewAI, OpenAI, and more.

P2P multimodal agent orchestration harness and universal automation system

Local MCP daemon that compresses your codebase before sending it to Claude 41-89% token reduction

A deterministic agentic workflow framework

High-performance LLM gateway in Go. 35x less RAM than Node.js version.

High-performance LLM gateway in Go. 35x less RAM than Node.js version.

No repository description published.

A pure-Go port of pi (earendil-works/pi) — the pi-ai unified multi-provider LLM API, pi-agent-core agent loop, and pi-coding-agent, native in Go with no Node.js runtime. Anthropic/OpenAI/Google, 999-model catalog.

No repository description published.

The Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted, no vendor lock-in. ( 55x faster than litellm )

No repository description published.

Supercharged vibe coding — local proxy that auto-routes Claude Code requests to any provider with transparent API translation, smart routing, and failover. Single Go binary with super ease to use TUI config wizard and live usage monitor.

A blazing-fast Markdown-to-ANSI CLI for terminal rendering, LLM streaming, and syntax highlighting. 📝

Agent Session Manager - A comprehensive Elixir library for managing AI agent sessions, state persistence, conversation context, and multi-agent orchestration workflows

Git-native AI agent co-harness — MCP server, static guards, and agentic evaluator for LLM-assisted coding