# HarnessRouter/harnessrouter > Self-hosted gateway that turns existing agent harnesses (Codex, Claude Code, Aider, etc.) into pluggable backends behind one OpenAI-compatible API via the open Unified Harness Protocol. - Magnitude: 3.3 out of 10 — Breakout - Stars: 3,668 total · +5 stars measured 2026-10-26, 11:33–13:13 UTC, ≈ 28 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-08-09 · Last push: 2026-10-26 - GitHub: https://github.com/HarnessRouter/harnessrouter · Homepage: https://harnessrouter.ai/ · Page: https://gitnova.dev/en/r/HarnessRouter/harnessrouter ## Useful for - Run HarnessRouter in Docker and connect your own model provider key - Switch harnesses and models via metadata.harness_id without changing product code - Integrate agent tasks into your backend through the OpenAI Responses-compatible API ## Why it’s here - Star-counter measurements on 2026-10-26 (UTC), 11:33–13:13: 3663 → 3668 stars (+5). This is the change over that interval. - Estimated end-of-day forecast: about +28 stars, using observed gains and the previous day. - Over the last two days the pace is 2.4× that of the previous week and a half. - GitHub Trending Python today: #16, +95 stars. - About 9 forks a day — people are taking the code. - Recent forks include notable developers: @mvanhorn (5,724 followers). ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 393 - Issues and pull requests: 583 - Watchers: 23 - Average over the last week: 77 per day - Usual pace: 29 per day - Stars in the last hour (measured): 8 - Latest release: v0.37.1 (2026-10-26) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-09-27 … 2026-10-26: 33, 42, 30, 11, 21, 42, 11, 16, 12, 10, 17, 22, 10, 11, 6, 19, 16, 4, 14, 55, 39, 22, 20, 15, 48, 41, 35, 265, 106, 5 ## Spotted in now - GitHub Trending Python today: #16, +95 stars ## Similar by description 1. **QuantumNous/new-api** — 3.3 · Steady · Language models · Go · +45 stars measured 2026-10-26, 00:15–13:14 UTC, ≈ 79 by evening Self-hosted AI gateway that aggregates multiple LLM providers behind a unified OpenAI-, Claude-, or Gemini-compatible API with routing, access, and cost management. Full card: https://gitnova.dev/en/r/QuantumNous/new-api.md 2. **Wei-Shaw/sub2api** — 3.0 · Steady · AI agents · Go · +49 stars measured 2026-10-26, 00:14–13:14 UTC, ≈ 81 by evening An API gateway for AI subscription services that unifies access to Claude, OpenAI, Gemini and Grok behind one interface and lets users share subscription quotas. Full card: https://gitnova.dev/en/r/Wei-Shaw/sub2api.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-26 13:24 UTC, updated every 30 minutes.