AMAP-ML/LongHorizon-Harness

LongHorizon-Harness

Loop Engineering for Computer-Use Agents

Give Claude Code, Codex, OpenCode, or DeepSeek Harness a goal once. Keep it working across desktop apps and the terminal for dozens of hours.

Plan → act → verify → checkpoint or recover → repeat — until the work is actually done.

  

Usage · The Loop · Computer Use · Results · Project Website · 简体中文

The model determines what an agent can do in one round. LongHorizon-Harness engineers the loop around it: what to do next, how to verify the result in the real computer, what progress to preserve, and how to continue after failure or context refresh.

A Loop Engineering system for Claude Code, Codex, OpenCode, and DeepSeek Harness. One-command install, ready to run.

LongHorizon-Harness turns existing agents into long-running computer-use systems. Across desktop apps and the terminal CLI, it continuously recovers the goal and verified state, selects the next bounded step, executes it with a fresh context, checks the actual result, and then checkpoints accepted progress or feeds failure evidence into the next round. It does not train a new model or replace an existing agent; it provides the durable execution loop around one.

✨ News

• [v0.1.7 · 2026-08-20] A finished run is no longer a dead end: the workbench is now a conversation.Read the reply, type a follow-up, and the run continues on its own round ledger instead of replanning from scratch.A message you send mid-round is claimed by the very next round, so stopping and continuing never drops it.Also adds --reasoning-effort for every role (with --manager-reasoning-effort and friends to override one), forwarded to whichever backend exposes it.

The transcript now reads in strict chronological order, and a graceful stop escalates to a force stop only when a worker ignores it. - [v0.1.6 · 2026-08-15] Added OpenCode CLI support.LongHorizon-Harness can now run opencode run prompt as --agent opencode, with role-scoped read/write permissions, OpenCode API endpoint overrides, normalized JSON results, and CLI/config/doctor integration.The Web workbench can select OpenCode Harness and its model independently for each role. - [v0.1.5 · 2026-08-14] Added phase-1 DeepSeek Harness CLI support.

LongHorizon-Harness can now run dsh --profile headless as --agent deepseek_harness, with an isolated DSH_HOME, role-scoped read/write permissions, DeepSeek API endpoint overrides, normalized JSONL results, and CLI/config/doctor integration.The Web workbench can select DeepSeek Harness and its model independently for each role.GUI computer-use and MCP support will follow in a later phase;see the CLI setup. - [v0.1.4 · 2026-08-11] The new Dashboard has landed: a React/FastAPI workbench you can drive entirely from the browser.

Start a task, choose a backend and model per role, answer approvals, send an instruction mid-run, and stop or restart a run.Launch it with lh-harness web;see Run a task in the browser. - [2026-08-10] Added the Terminal-Bench 2.1 evaluation. - [v0.1.3 · 2026-08-07] Every run now ends with a plain-language reply that answers your task from the verified state alone.

Tasks act on the directory you launched from by default, and the console reports each round as it happens. - [2026-08-06] LongHorizon-Harness reaches #1 on the Hugging Face Daily Papers weekly ranking. - [v0.1.2 · 2026-08-06] Adds unified computer-use plugin management, stronger auditor read-only checks and role isolation, reliable process cleanup, and expanded doctor diagnostics.See Manage computer-use plugins.

🚀 We’re iterating rapidly. Stay tuned!

Video Demo

https://github.com/user-attachments/assets/ca8b77ce-9220-4d85-a272-b346009b2454

Open the promotional video (1440p MP4)

Loop Engineering for real computer environments.

Give LongHorizon-Harness an outcome. It repeatedly turns the remaining work into a bounded step, performs that step on the right computer surface, checks what actually happened, and carries the verified result into the next round.

flowchart LR
S["Original goal +
verified state"] --> P["Plan the next
bounded step"]
P --> A["Act in a desktop app or CLI
with fresh context"]
A --> V["Verify files, UI, logs, and tests
in the real environment"]
V -->|Pass| C["Checkpoint
verified progress"]
V -->|Fail| R["Record evidence
and recover"]
C --> D{"Task complete?"}
R --> S
D -->|No| S
D -->|Yes| F["Verified result"]

This is Loop Engineering: designing the execution, verification, correction, and recovery loop around the agent — not just the prompt for a single turn.

One loop. Three focused responsibilities.

The roles are implementation boundaries inside the loop, not three agents independently growing their own versions of the task.

Only results that pass independent verification become trusted task state. A rejected result remains evidence, not progress. When a context is refreshed, an action fails, or a deliverable does not pass inspection, the next round starts from the original goal and the last verified checkpoint, then continues from what remains.

Desktop apps and CLI. One continuous task.

LongHorizon-Harness supports both GUI and CLI workflows.

One task can begin in a browser, move to the command line for data processing, continue in desktop software to produce an artifact, and return to the terminal for validation or debugging. The goal, progress, and evidence remain under the same state-management system throughout.

Any model. Any agent backend.

LongHorizon-Harness is not tied to a specific model or agent backend. Existing models and agents connect through configuration without changing their original workflows.

A lightweight AgentAdapter preserves each agent's native execution loop while LongHorizon-Harness coordinates role boundaries, verified task state, and cross-round progress around it.

Use one model for all three roles, or combine different models and backends to balance quality, speed, and cost.

Hundreds of real tasks. Measured gains.

LongHorizon-Harness is not demonstrated only on a handful of carefully selected success cases.

We ran it on hundreds of complex tasks across GUI, CLI, and mixed computer environments:

Same model. Same execution backend. Only the harness changes.

~50% → ~80%

GUI + CLI completion

WeaveBench

3×

Full desktop-task completion

OSWorld 2.0

69.7% → 77.2%

Code + CLI success

Terminal-Bench 2.1 · 24% fewer tokens

📊 Full benchmark results and experimental settings

All rows use Qwen 3.7-Plus as the backbone and Claude Code as the execution backend.

Full result tables and case trajectories are available on the LongHorizon-Harness project website.

One command. Full visibility.

Installation

Steps 1–2 are once per machine; step 3 is once per project. Then run tasks from the browser (step 4) or the command line (step 5).

Requirements

... (truncated at the site's per-page length limit; see the source link below for the full text.)