Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
cocoindex
AI repositoriesIncremental engine for long horizon agents 🌟 Star if you like it!
git clone https://github.com/cocoindex-io/cocoindex.git -
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 -
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 -
opencorvus
Agents & frameworksDIY your own agent team harness for long-horizon agent work
git clone https://github.com/yangheng95/opencorvus.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 -
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 -
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 -
MoonshotAI: Kimi K3
ModelsKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
moonshotai/kimi-k3 -
MiniMax: MiniMax M3
ModelsMiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
minimax/minimax-m3 -
MoonshotAI: Kimi K3 (batch)
ModelsKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
moonshotai/kimi-k3:batch -
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
reflection/beam-1.0-501b-a23b -
MiniMax: MiniMax M3 (batch)
ModelsMiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
minimax/minimax-m3:batch -
Z.ai: GLM 5.3
ModelsGLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
z-ai/glm-5.3 -
Anthropic: Claude Opus 5
ModelsClaude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
anthropic/claude-opus-5 -
Z.ai: GLM 5.2
ModelsGLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
z-ai/glm-5.2 -
Z.ai: GLM 5
ModelsGLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
z-ai/glm-5 -
Anthropic: Claude Opus 5.5
ModelsClaude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
anthropic/claude-opus-5.5 -
Z.ai: GLM 5.3 (batch)
ModelsGLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
z-ai/glm-5.3:batch -
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
anthropic/claude-opus-5:batch -
Z.ai: GLM 5.2 (batch)
ModelsGLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
z-ai/glm-5.2:batch -
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
anthropic/claude-opus-5.5:batch -
Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...
bytedance-seed/seed-2-1-turbo -
Z.ai: GLM 5.3 Flash
ModelsGLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
z-ai/glm-5.3-flash
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.