Long-running agents need more than a chat history.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Long-running agents need more than a chat history. LoopX is a provider-neutral, local-first control plane for builders running long-horizon work across Codex, Claude Code, Cursor, and other agent harnesses. It helps you keep multi-day work reviewable and restartable by preserving objectives, gates, todos, evidence, quota, and handoffs across turns instead of leaving that state inside the agent runtime. Key features: • Durable goal state – keeps the active objective, scope, todos, gates, evidence, and quota in one control layer • Harness-neutral design – runs on top of Codex, Claude Code, C
Posted by Dan Kornas (99.2k followers) 1 h ago · 5 likes · 608 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- NVIDIA released a fast speaker-labeling model today: Nemotron 3 Diarization. Like all of… — @kwindla
- Built a DiffusionGemma perf test: 100% local metasearch engine using the Jev-like API on… — @mmastrac
- ➡️ Coming soon: Let's Learn GitHub Copilot SDK — @github
- The context developers need to build better applications has always lived in Box. Now it… — @Box
- Missed AGNTCon + MCPCon EU live? We’ve got you. — @AgenticAIFdn
- Testing Mimo-v2.6-flash has started. — @ItsmeAjayKV
- AI Agent 跑完任务后，最麻烦的往往不是结果，而是过程没法回头看。 — @bkdgiffug
- finally, my AI voice clone can say "let's take this offline" and "you're on mute" in my… — @DynamicWebPaige
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22.6k posts from 5k X accounts over the last 21 days, 2.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 16:31 UTC. Full method.