InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. GLM-5

    AI repositories

    GLM-5: From Vibe Coding to Agentic Engineering

    Stale GitHub, zai-org 7,328 ★Apache-2.0Updated 53 days ago

    git clone https://github.com/zai-org/GLM-5.git
  2. cocoindex

    AI repositories

    Incremental engine for long horizon agents 🌟 Star if you like it!

    Indexed GitHub, cocoindex-io 11.9k ★Apache-2.0Updated 2 days ago

    git clone https://github.com/cocoindex-io/cocoindex.git
  3. Long-Horizon-Terminal-Bench

    Datasets & benchmarks

    Hugging Face dataset by IntelligenceLab

    Stale Hugging Face Hub, IntelligenceLab 140 ♥apache-2.0Updated 36 days ago

    IntelligenceLab/Long-Horizon-Terminal-Bench
  4. Recuris

    Skills

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

    Stale GitHub, Gen-Verse 238 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/Gen-Verse/Recuris.git
  5. loopx

    Agents & frameworks

    The 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.

    Indexed GitHub, loopx-project 6,685 ★Apache-2.0Updated today

    git clone https://github.com/loopx-project/loopx.git
  6. ContextLattice

    Agents & frameworks

    The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.

    Indexed GitHub, sheawinkler 155 ★Apache-2.0Updated today

    git clone https://github.com/sheawinkler/ContextLattice.git
  7. apex-agents

    Datasets & benchmarks

    Hugging Face dataset by mercor

    Stale Hugging Face Hub, mercor 207 ♥cc-by-4.0Updated 5 months ago 1 note

    mercor/apex-agents
  8. Awesome-AI4AI

    Datasets & benchmarks

    Updated 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.

    Stale GitHub, KaiWU5 218 ★MITUpdated 8 days ago

    git clone https://github.com/KaiWU5/Awesome-AI4AI.git
  9. WeVisCut

    Models

    any to any model by tencent · transformers

    Stale Hugging Face Hub, tencent 26 ♥otherUpdated 17 days ago

    tencent/WeVisCut
  10. zenith

    MCP servers

    Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.

    Stale GitHub, Intelligent-Internet 350 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/Intelligent-Internet/zenith.git
  11. opencorvus

    Agents & frameworks

    DIY your own agent team harness for long-horizon agent work

    Indexed GitHub, yangheng95 309 ★MITUpdated 4 days ago

    git clone https://github.com/yangheng95/opencorvus.git
  12. doc2harness

    Datasets & benchmarks

    Official Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "

    Stale GitHub, YuyaoGe 116 ★Custom licence (see repository)Updated 20 days ago

    git clone https://github.com/YuyaoGe/doc2harness.git
  13. deer-flow

    Agents & frameworks

    An 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.

    Indexed GitHub, bytedance 85.4k ★MITUpdated today

    git clone https://github.com/bytedance/deer-flow.git
  14. OSWorld-V2

    Datasets & benchmarks

    OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

    Indexed GitHub, xlang-ai 421 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/xlang-ai/OSWorld-V2.git
  15. alem-env

    Datasets & benchmarks

    Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).

    Stale GitHub, alem-world 57 ★MITUpdated 11 days ago

    git clone https://github.com/alem-world/alem-env.git
  16. bg3-agent-harness

    MCP servers

    An 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.

    Stale GitHub, Bogzx 33 ★MITUpdated 7 days ago

    git clone https://github.com/Bogzx/bg3-agent-harness.git
  17. mira

    Agents & frameworks

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

    Indexed GitHub, taylorsatula 485 ★AGPL-3.0Updated today

    git clone https://github.com/taylorsatula/mira.git
  18. 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.

    Stale GitHub, VibeBench 112 ★MITUpdated 5 months ago

    git clone https://github.com/VibeBench/VibeSearchBench.git
  19. Turn any repository AI-first and run resumable, long-horizon Deep Work Plans with any coding agent — an installable, MIT-licensed agent skill.

    Indexed GitHub, DailybotHQ 24 ★MITUpdated today

    git clone https://github.com/DailybotHQ/deepworkplan-skill.git
  20. 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.

    Stale GitHub, Tiger3807861189 2,977 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/Tiger3807861189/J-Space-Cognition-Suite.git
  21. forest

    Agents & frameworks

    FOREST 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

    Stale GitHub, mikamikasuki 355 ★Apache-2.0Updated 20 days ago

    git clone https://github.com/mikamikasuki/forest.git
  22. vibe-check-mcp-server

    Tools & apps

    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

    Stale GitHub, PV-Bhat 504 ★MITUpdated 15 days ago

    git clone https://github.com/PV-Bhat/vibe-check-mcp-server.git
  23. Agentic, 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.

    Stale GitHub, wanshuiyin 75 ★MITUpdated 10 days ago

    git clone https://github.com/wanshuiyin/ARIS-Movie-Director.git
  24. Tencent: Hy4

    Models

    The 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...

    Indexed OpenRouter model list, tencent Updated 12 days ago

    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.