LoopX：跨会话管理智能体长任务

Turn long-horizon goals into verifiable results. A local-first semantic control plane and research workbench for long-running agent teams…

LoopX 2.0 Turn long-horizon goals into verifiable results. A local-first semantic control plane and research workbench for long-running agent teams, across sessions and runtimes. Keep goals, decisions, ownership and evidence durable. Work with Codex, Claude Code, DeepSeek Harness and other runtimes you already use. Get started · Why LoopX · See it in action · Evidence · Contribute · Docs · 简体中文 Start in two steps With Python 3.11+ and Node.js 22.22.3+ (24 LTS recommended), install once: python3 -m pip install --upgrade loopx && loopx workflow-skills --install Restart your Agent host, open your project, then give Codex a concrete task: $loopx speed up this project's slowest workflow; compare approaches and verify the gains Claude Code uses /loopx <complex task>. Other hosts, install options and upgrades ↓ 📰 News 2026-10-25 · 🤝 Long-horizon agent research: collaborators welcome — Academic labs and industry teams: collaborate on feedback, replanning and reproducible evaluation on EdgeBench and real-world tasks, measuring outcomes and total cost under comparable budgets. Discuss collaboration. 2026-10-20 · 🚀 LoopX 2.0 — A shared TypeScript control plane and long-horizon research workbench. Migration guide · Engineering story. 2026-10-14 · 🤖 Agentic software — Connecting goals, evidence and human feedback to engineering delivery. 2026-10-02 · 🧠 Long-horizon bootstrapping & RSI — Four months of developing LoopX with LoopX: public project history and a design perspective on system-level self-improvement. 2026-09-18 · 🧪 LoopX × LHTB — A 46-task long-horizon agent study comparing Plain Codex, native Goal and LoopX Heartbeat, with task-level results, methodology and comparison limits. 2026-09-06 · 🎉 LoopX 1.0 — A Personal Agent Workspace to follow agent work, act on decisions, and inspect delivered results across sessions. Workspace guide. 2026-08-02 · ⏱️ 200+ hour trajectories shared on X — Early owner-run examples spanning 200+ elapsed hours drew broad attention on X, showing work across execution, waits, human decisions and recovery. Trajectories and limits. All releases Why LoopX An agent can finish a task in one session. Long-running work is harder: objectives change, owner decisions appear, evidence goes stale, and agents hand work to peers. A timer can keep a loop running without making it useful. Continue without starting over. Keep the Goal, accepted requirements, decisions and evidence across sessions and restarts. Coordinate without losing ownership. Connect delegated work, dependent artifacts, review and returned results while keeping responsibility explicit. Judge progress by what changed. Inspect deliverables, supporting and refuting evidence, costs and the next decision—not just activity. Your Agent runtime supplies the model and tools. LoopX’s semantic control plane preserves goals, acceptance, decisions, ownership and evidence across sessions and runtimes for engineering, research and operations. Agents and people use those facts to reassess what to do next. Human authorization still governs protected actions. What you want to do Start here Keep a coding or research agent working across sessions Install and start Manage personal projects, schedules and decisions in one place Personal Agent Workspace Let agents collaborate and deliver verifiable results Agent collaboration guide LoopX keeps the durable control state in one compact layer: Agent runtimes execute the work. LoopX governs the state that lets engineering, research, discovery, and operations loops continue across runs. It is not another agent framework or a provider-specific orchestration runtime. How the control plane works and where it fits A useful mental model is an agent-native Kanban for long-running work. Cards carry identity, authority, evidence, and continuation. Moves are validated operators such as claim, gate, monitor, and writeback. The board is a projection; LoopX state remains the source of truth. Registered agents are peers. Claims, leases, task boundaries, capabilities, and typed continuation decide who acts next; no durable leader identity is required. LoopX is useful when you run: multi-day engineering, research, benchmark, or experiment objectives; issue and PR loops that must preserve scope, evidence, and review state; recurring heartbeat or monitor work; projects with owner, safety, publication, or private-data gates; peer-agent teams where ownership, leases, and handoff matter; creator, research, or operations workflows whose progress must remain legible to a non-engineering operator. LoopX is not an autonomous production controller. Dangerous permissions, publishing, production writes, and final ownership stay with the human. See LoopX in Action Watch the research-workbench film · 86s · transcripts, subtitles and sources. Recorded App excerpts, synthetic examples and illustrations are labelled. Research that can continue Open a Goal to inspect its work, responsible Agents and recorded Explore history. Use Deep analysis to inspect a registered trajectory, its citations, native outcome readback and separately measured costs. An Agent prepares the source; opening a page or reading a result does not start a model call. Explicit analysis uses the configured host and account. Keep supported, refuted and unknown findings visible. Inspect why an approach changed or continued, then carry the evidence into the next attempt. Meet the Personal Agent Workspace Keep long-horizon goals in one local-first workspace. Goals, attention, conversations, tasks, files, schedules, and recovery stay durable across days, restarts, and harnesses. Reopen a project, inspect the previous turn’s state and evidence, and continue the next permitted action. LoopX brings these long-horizon control states into the Personal Workspace. It gives you one place to: see what needs you, what is running, what is being watched, and what is scheduled or stopped; configure Goal capabilities, distinguish machine defaults from Goal overrides, and