Go
helixml/helix
♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️
★ 829
Stars
85 forks · 152 open issues
+5.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
38.3
Momentum / 100
see the breakdown below
3y ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 4.5 | +5.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 10.3 | last week ran 1.69× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 8.5 | 829 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 38.3 | sum of the above |
Detail
| Topics | agentsapigenaiglmgolanghelmk8skimillmllm-agentllm-servingopenaiopenapiqwenragself-hostedswaggerswarm |
| Matched on | AI Agents (llm-agent) LLM & Inference (llm-serving) |
| Short window | +5 stars over 7 days = 0.7/day |
| Long window | +11 stars over 26 days = 0.4/day |
| Lifetime average | 0.74 stars/day over 1,115 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |