#llm

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.

CLI that auto-detects AI provider credentials and shows usage quotas in a TUI or JSON

No repository description published.

A modern bun framework that is easy and AI first

Blazing fast Go port of gemini-web2api. Convert Google Gemini web into OpenAI-compatible API. Zero cost, single static binary.

Plugin lifecycle manager for the intisy-ai AI-proxy ecosystem.

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

Governed AI agents that actually do the work - in the cloud or on your own machine - across business systems, real browser tabs and real Android apps. Visual builder, MCP server, and official SDKs in 9 languages.

Elixir SDK for the Amp CLI — provides a comprehensive client library for interacting with Amp's AI-powered coding agent, including thread management, tool orchestration, streaming responses, and programmatic access to Amp's full feature set from Elixir/OTP applications

Parse partial JSON generated by LLM

TypeSafe platform bridge for Symfony AI

ClickUp MCP Server - Integrate ClickUp project management with AI through Model Context Protocol

A stateful, graph-based agent runtime for Go — LangGraph's core ideas in 419 dependency-free lines

Evaluate LLMs side-by-side. Benchmark AI models and coding agents across providers like OpenAI, Google, Anthropic, DeepSeek, and more. Supports custom tasks, structured JSON responses, tool use, and LLM-as-judge validation. Originally created by Petr Malik as MindTrial.

Adversary simulation and Red teaming platform with AI

test

No repository description published.

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

No repository description published.

An isolated, secure execution sandbox for AI coding agents

Switch Claude Code's backend per terminal — one command, no global config.

Zero-dependency prompt compression for LLM applications. One deterministic algorithm, three native SDKs (TypeScript/Bun, Rust, Go) with byte-identical output. No ML model, no downloads.

CLI tool that explains programming errors using a locally-embedded LLM. No API keys. No internet. No patience required.

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

A local MITM proxy between AI coding agents and their APIs: it masks secrets found in outbound prompts with shape-preserving surrogates and restores them in the response. Go, runs entirely on your machine.

Turns a plain folder into a persistent, evidence-first memory: episodic recall with cite-or-abstain answers, distilled convictions, and a deterministic constraint shield. Go library plus CLI, offline, git as the audit trail.

Pi Agent extension that bridges MCP servers to the LLM via two dynamic-context tools (CallMcpTool + FetchMcpResource). Filesystem-is-everything: each MCP server is described by meta.json + tools/*.json, loaded into context on session start.

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

Self-hosted AI gateway — route, observe, and control your LLM API traffic. OpenAI ↔ Anthropic protocol translation, cost-based smart routing, per-user budgets, built-in dashboard. Zero dependencies.