LLMOps & Gateways

Deterministic guardrails that don't break agents

Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by hundreds of contributors

Doulor Cloud — an all-in-one cloud resource distribution platform: subdomains / domain email / R2 direct-link cloud drive / personal business card / AI API relay. Pure static frontend + Cloudflare Workers + D1 + R2.

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, a

Agent Skills as a Memory Layer

Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.

Your friendly, blazing-fast, self-hostable AI gateway

Backend powering unorouter.com. Unified AI gateway aggregating 12+ providers with billing, channel routing, and OpenAI/Claude/Gemini compatible relay.

Paseo plugin: per-turn LLM token usage, cache and cost ledger for Claude, Codex and other agents

Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and garbage mid-stream, before the user sees a bad token. Works with any OpenAI-compatible API.

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

OpenAI-compatible proxy for ChatGPT Codex Responses API

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.

Claude Code plugin that streams your sessions to Rius as OpenTelemetry traces: prompts, model calls, tokens, tool calls and subagents.

Where rain falls, memories bloom again. A self-hostable AI long-term memory and chat gateway. Self-hosted AI memory & chat gateway for long-term conversations.

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

The Cloud-Native API Gateway and AI Gateway

Official download and usage instructions for the public-service assistant Android app.

Supercharge Your LLM Application Evaluations 🚀

An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.

🦍 The API and AI Gateway

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Evidence-grounded CV/job matching with hybrid LLM routing, explicit requirement satisfaction, abstention, deterministic guardrails, and held-out evaluation.

OpenTelemetry Instrumentation for AI Observability

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

Open-source guardrails for AI agents powered by decision models like Jev; checks prompts, retrieved content, tool calls and responses for prompt injection, jailbreaks and secret/PII leaks.

cut Claude Code token usage by rendering text context as images