Long Horizon Agents

Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

SpineCodex: Let your Codex work, evolve, and scale on a SpineTree — up to 10× effective context and 89% more SWE-Milestone tasks resolved at 27% lower cost.

The AI agent that always stays sharp. 200k+ tokens of work in a 64k context. Sandboxed for unattended overnight runs. Sub-10ms Go CLI, any model.

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.

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates.

Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok — multi-task ledger loop (related or not), host-portable (re-send the prompt to continue), clean-context supervisor, verified gates. Markdown library (loop-graph · quest), not a framework.

Manifold is an experimental platform for enabling long horizon workflow automation using teams of AI assistants.

CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.

a best-effort approximation of a synthetic entity complete with all of the primatives required for long-horizon persistance. batteries included.

J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research. | 哔哩哔哩：Tiger380 — https://space.bilibili.com/3494375382321675