Havuz

Your agent’s trace says “success” but the answer is wrong. Tracedown finds the step that caused it and replays the run with a fix.

A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi

One control plane for every AI asset — MCP servers, skills, agents, AI apps. Self-hosted ledger with lifecycle state machine, 85 permission

Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs tha

Commented SHIP? Full briefs for 3 pile-two AI engineering projects: LLM Ops, Agent Evals, Auto Routing. What to build, what to measure, what

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）

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

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

Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini and every other vendor. Any SDK, any model, any tool.

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

Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, ch

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

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

Local, self-hosted agent infrastructure — one endpoint for every AI client (Claude Code, Codex CLI, Gemini CLI, OpenCode). Unified model acc

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

200+ AI, Gen AI, LLM, agentic AI, Forward Deployed Engineer (FDE), AI systems architect, applied AI, LLMOps and AI platform engineering inte

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

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

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

Cheaper and better Greptile alternative runs on your own github actions.

Aixle Flow — orchestrate coding agents through durable, inspectable workflows.

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

Proxima lets existing GPUs serve 4x more concurrent requests

The open-source agentic framework to build, orchestrate, and operate production AI agents.

Deterministic-first execution engine for agent workflows in Go: the LLM extracts at the edge, a deterministic state machine decides. Zero de

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

agentacct, coding agent oturumlarını yerel verilerden toplayıp yapılan işleri, kullanılan araçları, kontrolleri, token tüketimini ve tahmini maliyeti dashboard ile TUI üzerinden gösterir.

Neden yükseliyor · 65 günde 755 yıldıza ve son 28 günde 198 commite ulaşması hızlı ilgi ve aktif geliştirme sinyali veriyor; ancak aynı dönemde yalnızca 2 farklı yazar bulunması katkı tabanının dar olduğunu gösteriyor. Bu ilginin kesin nedenini ölçümlerden çıkarmak mümkün değil.

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

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

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

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

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

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

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

Waku, yerel SQLite memory, agent loop ve eval araçlarını bir araya getiren, Python tabanlı kişisel AI assistant uygulamasıdır.

Neden yükseliyor · 79 günlük bir repo için 1.849 yıldızın yanında son 28 günde 30 commit ve 7 farklı yazar bulunması görünür ilgi ve devam eden geliştirme gösteriyor. README'nin sade, okunabilir agent loop ve entegre memory/eval yaklaşımı da projeyi agent harness arayan geliştiricilere çekici kılıyor; bu metrikler benimsenme veya üretim başarısını tek başına kanıtlamıyor.

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

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

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

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity re

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

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

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

Open-source control plane for private, governed enterprise AI — one gateway for every model, composable governed pipelines, and apps your wh

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Agentic Runtime

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

Free, local, open-source LLM cost analyzer - see where your LLM bill leaks, on your machine.

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

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

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