Havuz

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model

Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command,

Reference implementation of a list-building path for GTM engineers: a plain-English campaign brief becomes a deduped, qualified, enriched, s

👻 MoEWatch: A lightweight diagnostic and audit library for Mixture-of-Experts (MoE) models in HuggingFace Transformers — the pytest for MoE

The whole eve stack. On your own machine. Durable Postgres sessions, a Docker sandbox, memory, approvals, schedules, 1,070 tool integrations

Local CLI for auditing AI agent skills, conflicts, duplicates, safety risks, and context cost across coding agents.

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

ZKE（Z Kubernetes Engine）：AI 原生的 Kubernetes 云操作环境，桌面式多集群控制台加受控 AIOps Agent，基于 Server + Agent 与 QUIC/mTLS，适用于私有云、混合云及边缘环境

Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship.

Radicalbit AI Gateway

An open source, Native AI Gateway and LLM proxy built in Rust

Six Claude Code skills that harden Opus 4.8 toward frontier behavior. Written by Fable 5, pressure-tested on the target model with transcrip

Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely release self-hosted models behind

Auto-delegation, status truth, and cost-aware model routing for OpenClaw agents

Operational doctrine for practical AI systems design.

Self-hosted LLM router. Cost effective, deterministic, and fast. Secure and private by default.

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin

Lightweight cost observability for every API call in your stack. Track LLM tokens, database ops, and external services from your terminal.

LLM spend tracking and budgets for Rails — by user, feature, or any tag, in your own database, no proxy.

Phoenix-native LLM evaluation, prompt testing, model comparison, red teaming, and observability for Elixir

Economical human-readable logs and structural (event pattern) retrieval for agentic trajectories

A 21-day hands-on journey to mastering AI for DevOps — covering LLMs, GenAI, CI/CD, Kubernetes, cloud, automation, and AI-powered DevOps pro

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.

Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.

Observable diagnostics, failure attribution, metrics, and no-key replay for multi-agent runtimes.

Enterprise-ready CI/CD reference for Microsoft Foundry AI agents, with parallel GitHub Actions and Azure DevOps pipelines, evaluation-driven

Practical LLM evaluation for teams that ship to production. Deterministic + LLM-as-judge evaluators, dataset support, CI/CD integration.

Proxima lets existing GPUs serve 4x more concurrent requests

Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently ro

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

A token-spend profiler and cost-regression gate for AI agents.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

Enterprise-grade sovereign AI for organizations where SaaS AI isn’t an option.

A production-ready toolkit to accelerate and automate the end-to-end lifecycle of AI Agent development.

Deterministic cost / loop / time budgets · full observability · crash-resumable runs · human-approval gates · a memory you own. Self-hosted.

Open-source, self-hosted AI-assisted operations for Kubernetes and Linux. Start here for source, architecture, deployment, and contributions

Session-layer circuit breaker for LLM & agent traffic — a transparent streaming proxy that meters every session and kills the one that goes

Snapshot testing for LLM apps and agents, built to run locally and block regressions in CI.

Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

LLM providers frequently update their models without changing the model string or announcing behavioral shifts. These changes cause silent r

Know when an AI conversation thread is still safe to continue — a deterministic, dependency-free continuity planner.

Typed evaluation for OpenCode skills and AI agents: capability, regression and product checks; provider-neutral evidence grading, provenance

Transparent LLM gateway trace recorder · sub2api / CLIProxyAPI / new-api 的 LLM 网关流量录制器

Store agent traces remotely. Analyze them locally. Keep control of the data.

A production-oriented LLM engineering platform with OpenAI-compatible serving, streaming, observability, evaluation, reproducible experiment

Distil an expensive LLM API call on a narrow task into a small local model: capture traffic, curate, LoRA fine-tune with MLX on Apple Silico