Havuz

Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com

Run-aware token governance for multi-agent systems.

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

Radicalbit AI Gateway

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

End-to-end Langfuse workshop using a TypeScript Agent to teach the AI engineering loop: tracing, prompt management, monitoring, datasets, ex

Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

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

Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply

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

Operational doctrine for practical AI systems design.

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.

Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token

A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and

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

Prove an AI-written fix actually fixes the bug. mini-ork certify reproduces the bug against your repo's own code, attacks the patch with gen

Audit any agent decision across its past, present, and future, on one typed graph.

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

端到端智能体平台：把本机的 AI Agent 变成人人可用的 Web 产品（Vue 3 + Flask + Go WS 网关 + Docker 部署）

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.

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

CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledg

Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → paralleli

Benchmark LLMs head-to-head on your own prompts.

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

Behavioral regression testing for AI apps and agents: pytest plugin, behavior diff, CI gate, and document extraction metrics

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

Declarative Python SDK for building AI inference platforms on Kubernetes — bare machines to a served model, composed rather than hand-assemb

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.

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

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

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

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

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