#llmops

Code intelligence for humans, machines, and LLMs: receipts, metrics, and insights from your codebase.

🪢 Langfuse Ruby SDK - Instrument your LLM app and get detailed tracing/observability. Works with any LLM or framework

Turn your company's scattered knowledge into AI ready Books ✨

ThumbGate Pre-Action Checks derive rules from repeated failures, flag risky tool calls, hard-block detected secret leaks, and block matches in strict mode.

The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for calling more than 200+ LLMs.

Open-source AI governance gateway for EU teams: enforce PII, cost, model, data residency, and tool policies for LLMs and AI agents with signed evidence.

Self-hosted AI gateway and LLM proxy. OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock and 60+ providers, or serve vLLM/llama.cpp on your GPUs. Keys, budgets, guardrails, semantic cache, MCP

Full Portkey Admin API MCP server

Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.

Bionic is sovereign AI for the enterprise — ChatGPT-like AI that runs on-premise and can securely work with your sensitive data and systems.

The Requesty integration package for the Vercel AI SDK.

Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loops, and prove ROI across every repo.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

Production plumbing for LLM apps: context, cost, testing & governance — composable, framework-agnostic Python libraries.

Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.

Your prompts need tests too. Run prompts against real datasets, score outputs with LLM judges, version everything, and compare runs to see what got better.

🧯 Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.

fak — the Fused Agent Kernel: one Go binary for AI agent loops. Wrap Claude Code/Codex/Cursor, keep long sessions cache-efficient, route work per call, run local GGUF models, and adjudicate tool calls.