Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
GLM-5
AI repositoriesGLM-5: From Vibe Coding to Agentic Engineering
git clone https://github.com/zai-org/GLM-5.git -
cocoindex
AI repositoriesIncremental engine for long horizon agents 🌟 Star if you like it!
git clone https://github.com/cocoindex-io/cocoindex.git -
Long-Horizon-Terminal-Bench
Datasets & benchmarksHugging Face dataset by IntelligenceLab
IntelligenceLab/Long-Horizon-Terminal-Bench -
Recuris
SkillsRecursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
git clone https://github.com/Gen-Verse/Recuris.git -
loopx
Agents & frameworksThe control plane for 24/7 always-on agents. Turn long-horizon goals into verifiable results across Codex, Claude Code, and custom runtimes—from local SQLite to team scale.
git clone https://github.com/loopx-project/loopx.git -
ContextLattice
Agents & frameworksThe local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.
git clone https://github.com/sheawinkler/ContextLattice.git -
apex-agents
Datasets & benchmarksHugging Face dataset by mercor
mercor/apex-agents -
Awesome-AI4AI
Datasets & benchmarksUpdated weekly — until humanity achieves AI4AI. 1148 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.
git clone https://github.com/KaiWU5/Awesome-AI4AI.git -
WeVisCut
Modelsany to any model by tencent · transformers
tencent/WeVisCut -
zenith
MCP serversZenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
git clone https://github.com/Intelligent-Internet/zenith.git -
opencorvus
Agents & frameworksDIY your own agent team harness for long-horizon agent work
git clone https://github.com/yangheng95/opencorvus.git -
doc2harness
Datasets & benchmarksOfficial Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "
git clone https://github.com/YuyaoGe/doc2harness.git -
deer-flow
Agents & frameworksAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
git clone https://github.com/bytedance/deer-flow.git -
OSWorld-V2
Datasets & benchmarksOSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
git clone https://github.com/xlang-ai/OSWorld-V2.git -
alem-env
Datasets & benchmarksCan LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).
git clone https://github.com/alem-world/alem-env.git -
bg3-agent-harness
MCP serversAn AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.
git clone https://github.com/Bogzx/bg3-agent-harness.git -
mira
Agents & frameworksa best-effort approximation of a synthetic entity complete with all of the primatives required for long-horizon persistance. batteries included.
git clone https://github.com/taylorsatula/mira.git -
VibeSearchBench
Datasets & benchmarks🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.
git clone https://github.com/VibeBench/VibeSearchBench.git -
deepworkplan-skill
SkillsTurn any repository AI-first and run resumable, long-horizon Deep Work Plans with any coding agent — an installable, MIT-licensed agent skill.
git clone https://github.com/DailybotHQ/deepworkplan-skill.git -
J-Space-Cognition-Suite
SkillsJ-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.
git clone https://github.com/Tiger3807861189/J-Space-Cognition-Suite.git -
forest
Agents & frameworksFOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
git clone https://github.com/mikamikasuki/forest.git -
vibe-check-mcp-server
Tools & appsVibe 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
git clone https://github.com/PV-Bhat/vibe-check-mcp-server.git -
ARIS-Movie-Director
SkillsAgentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.
git clone https://github.com/wanshuiyin/ARIS-Movie-Director.git -
Tencent: Hy4
ModelsThe official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...
tencent/hy4
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.