Havuz

Local Anthropic-compatible AI gateway with cheap-first routing, quality gates, safe model handoffs, and an embedded cost dashboard.

Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your

Claude Code plugin that picks the model and effort for each turn (micro, low, medium, or high tier), advised by Jev, Clef, OpenAI, or a loca

Per-step LLM routing benchmark with 970 static labels, live SWE-bench evaluation, an open data pipeline, and a public leaderboard.

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type

TypeScript uygulamalarının `choice`, `noul` ve `score` biçimindeki sınırlı AI kararlarını farklı System One provider'ları üzerinden çalıştırmasını sağlayan bir runtime sunuyor.

Neden yükseliyor · Beş günlük repo için 60 yıldız ve son 28 günde 116 commit dikkat çekici başlangıç ilgisi ve geliştirme temposu gösteriyor. Ancak yalnızca 2 farklı yazar var; bu nedenle veriler geniş benimsemeyi veya sürdürülebilir topluluk desteğini henüz kanıtlamıyor.

Agent Router, bir görev için uygun AI coding agent'ı ve modeli seçip seçilen aracı Herdr içinde başlatan bir CLI'dır.

Neden yükseliyor · 10 günde 85 yıldız ve 122 commit dikkat çekiyor; ancak commit'lerin tek yazardan gelmesi bağımsız katkı veya benimseme kanıtı sunmuyor. Yükselişin özel nedenini mevcut verilerden belirlemek mümkün değil.

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, a

Open-source AI CLI and local MCP server connecting 25 clients—Claude Code, Cursor, Codex, ChatGPT, Hermes, and OpenClaw—to 2,000+ models/API

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m

Provider-pluggable orchestration runtime for multi-model AI inference. ( Sakana Fugu style )

ChatGPT 模型路由检测器：查看服务器报告的真实响应模型，自动识别路由降级，GPT Pro 计划降智查询。｜ChatGPT Model Route Inspector: view the actual response model reported by the server

Route complex Codex tasks to model-specific background workers with bounded concurrency and lead-agent verification.

Turn Fable or Opus into your agent orchestrator: plan coding work, assign capable Claude, Codex, or Grok agents, and personally verify the r

Private AI assistant, AI agent, and unified model proxy for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Skills, MCP, tools, channels, tas

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

Claude Code hooks that auto-switch model tier based on task complexity

AI inference gateway and control plane for multi-provider routing, policies, caching, tools, and observability.

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable syst

Local decision engine with typed, calibrated outputs (Noul/Choice/Score): cheap→strong cascade, ECE/Brier calibration, SystemOne protocol in

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker

Open-source Fugu: the open-source LLM orchestration brain.

Nexus — execution infrastructure for AI agents. Host agents in the cloud or behind NAT; let users attach and authorize their own computers a

不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/自愈/存档点提醒/审批策略自适应，官方钩子接入，不改 Hermes 核心代码

🏆Winning Project | ModelGate is a contract-aware AI control plane that ingests customer contracts, extracts SLA/privacy/routing constraints,

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

把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.

Local runtime for Claude Code and Codex — provider management, isolated sessions, routing and protocol translation.

Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent mod

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 Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

Portable model routing for Claude Code, specialized agents, ship gates, and Codex.

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isola

Route every prompt to the best LLM — for you specifically.

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the ro

Replay real agent traces through cheaper models to prove which swaps are safe.

Session-scoped GPT-5.6 agent routing for Claude Code

Claude skill + plugin that picks the right model and effort for every task: Opus plans, Haiku/Sonnet build, every step is verified, and it e

Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.

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

Personal, local-first desktop AI gateway for Windows, macOS, and Linux. Connect Claude Code, Codex, and Gemini CLI to OpenAI, Anthropic, Gem

Open-source, model-portable coding agent built for cost-efficient, verifiable software work—with model routing, progressive context, compact

Model router for AI coding agents: routes routine work to cheaper models with routing rules, 8 subagents, hooks and a CLI runner

Find out which model actually answers your Codex requests (detects silent model substitution, e.g. gpt-6-astra served by gpt-5.6-luna)

Finish coding-agent tasks with reviewed specs, frozen plans, bounded execution, adapter checks, and final proof. Provider-neutral lifecycle

An experiment-driven LLM engineering lab with 9 reproducible Python experiments exploring token economics, API costs, caching, context growt

Open-source model and reasoning effort router for Claude Code and Codex, using Jev or experimental self-hosted Laya.

Adaptive GPT-5.6 Sol, Terra, and Luna routing skill for Codex