Library
85,762 resources from 11 public sources. 53 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
-
alphora
Agents & frameworksA Production-Ready Framework for Building Composable AI Agents
git clone https://github.com/opencmit/alphora.git -
SoduWork
Agents & frameworksThe AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.
git clone https://github.com/mdiri-ai/SoduWork.git -
consensus-pipeline
Agents & frameworksMulti-agent department framework for long-form complex tasks, fighting AI hallucination, validated on academic research. 共识管线:多智能体部门长线任务解决框架,对抗AI幻觉,以学术研究为验证场景。
git clone https://github.com/fangqian616/consensus-pipeline.git -
awesome-agent-harness
Agents & frameworksgit clone https://github.com/AutoJunjie/awesome-agent-harness.git -
switch
Agents & frameworksOpen-source AI teammates in Slack, Teams, Discord, Telegram and Mattermost. Self-host it, with any agent harness and any model.
git clone https://github.com/sandbox-quantum/switch.git -
takt
Agents & frameworksTAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML
git clone https://github.com/nrslib/takt.git -
AgentCore
Agents & frameworksMulti-Agent AI 工作台 (AgentCore) — 真正的 Agent 团队协作,而非单 Agent 子任务派发
git clone https://github.com/Lawofall/AgentCore.git -
llm-sys-workshop
Agents & frameworks动手学习大模型系统
git clone https://github.com/tylerelyt/llm-sys-workshop.git -
RouterArena
Agents & frameworksRouterArena: An open framework for evaluating LLM routers with standardized datasets, metrics, an automated framework, and a live leaderboard.
git clone https://github.com/RouteWorks/RouterArena.git -
image-to-editable-ppt-skill
Agents & frameworksCodex skill for converting slide images, PDFs, and image-based PPTX files into editable PowerPoint decks.
git clone https://github.com/ningzimu/image-to-editable-ppt-skill.git -
skills
Agents & frameworksOMP-native pstack and orchestration skills for multi-agent coding workflows
git clone https://github.com/dsebban/skills.git -
Coffee-CLI
Agents & frameworksA clean AI terminal workspace. No hacks, no extra hooks, no lock-in — with quick input, folder switching, copy & paste, and image pasting. 极致清爽的 AI 终端工作平台。0 魔改、无额外 Hook、无绑定;支持快捷输入、目录切换、复制粘贴与图片粘贴。
git clone https://github.com/edison7009/Coffee-CLI.git -
FrontierAgent
Agents & frameworks🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
git clone https://github.com/ApodexAI/FrontierAgent.git -
zeroshot
Agents & frameworksMulti-agent graph harness for Claude Code, Codex and other coding agents. Separate agents review and test the work. Runs locally on your subscription.
git clone https://github.com/the-open-engine/zeroshot.git -
blades
Agents & frameworksBlades is a Go-based multimodal AI Agent framework.
git clone https://github.com/go-kratos/blades.git -
ppt-agent-skills
Agents & frameworksA code-driven presentation generation framework. 像构建软件工程一样生成演示文稿。
git clone https://github.com/sunbigfly/ppt-agent-skills.git -
Agents_Failure_Attribution
Agents & frameworksBenchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)
git clone https://github.com/ag2ai/Agents_Failure_Attribution.git -
powercontext
Agents & frameworksNot only memory but a full story
git clone https://github.com/oceanbase/powercontext.git -
AgentArk
Agents & frameworks[NeurIPS'26] Official Implementation for AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent(https://arxiv.org/abs/2602.03955)
git clone https://github.com/AIFrontierLab/AgentArk.git -
ir-sim
Agents & frameworksA Python-based lightweight robot simulator designed for navigation, control, and learning
git clone https://github.com/hanruihua/ir-sim.git -
negmas
Agents & frameworksNegotiation Multi-Agent System (A negotiation library designed for situated negotiations within business-like simulations)
git clone https://github.com/yasserfarouk/negmas.git -
Legion
Agents & frameworksA Python-based framework for building multi-agent systems with LLMs. Currently in pre-launch alpha.
git clone https://github.com/LLMP-io/Legion.git -
AgenticRAG-Survey
Agents & frameworksAgentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.
git clone https://github.com/asinghcsu/AgenticRAG-Survey.git -
pocketpaw
Agents & frameworksYour AI agent in 30 seconds. Not 30 hours. Self-hosted, open-source personal AI with desktop installer, multi-agent Command Center(Deep Work), and 7-layer security. Anthropic, OpenAI, or Ollama.
git clone https://github.com/pocketpaw/pocketpaw.git
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.