Arcee open-sources NAC agent harness; 489 tool calls, 67 passing tests on DeepSeek V4.1 Flash
MaziyarPanahi · x · 2026-09-12
Arcee AI open-sourced NAC (arcee-ai/nac), an agent harness for long-running ambitious tasks. It uses a thread-and-episode architecture: a central orchestrator plans and decomposes work but cannot execute commands or edit files — it only launches threads that return structured episode summaries, keeping long tasks aligned with original intent.
The author stress-tested DeepSeek V4.1 Flash's tool calling with it: 489 tool calls over 56 minutes, 67 passing tests, and a working explorer for real LIGO data. The repo has 238 stars, includes quickstart scripts, and cites inspiration from slate, nanocode, and pi.
More from coding & agent
- Developer streams an AI agent playing Minecraft all day via Codex, aiming to build an auto chicken farm — nickbaumann_ · 2026-09-12
- Why working with AI agents all day is exhausting: delegation adds mental load, not removes it — bendee983 · 2026-09-12
- "Codex is my main interface to the system": user says agent made Linux admin effortless — mark_k · 2026-09-12
- Alchemy's distilled project builds unified agent-friendly SDKs for 60+ SaaS services — samgoodwin89 · 2026-09-12
- RL on just 1,700 tasks lifts Kimi K2.7 across five coding benchmarks — echen · 2026-09-12
- Expected Parrot's universal remote cache hits 30M entries to fix AI-agent reproducibility — soumitrashukla9 · 2026-09-12