Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
grix
Agents & frameworksGrix : Work with agents like talking to people.
git clone https://github.com/askie/grix.git -
Everywhere
Agents & frameworksOn-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps.
git clone https://github.com/Sylinko/Everywhere.git -
FirstLight_CR
Agents & frameworksOffline Clash Royale AI agent research: native simulation, imitation learning, PPO, and interactive evaluation. 离线对局模拟、模仿学习、强化学习与交互评测。
git clone https://github.com/Jaasssoooonnnnn/FirstLight_CR.git -
ai-agents-from-zero
Agents & frameworks🚀 2026 最系统的 AI Agent 速成指南|智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
git clone https://github.com/didilili/ai-agents-from-zero.git -
powercontext
Agents & frameworksNot only memory but a full story
git clone https://github.com/oceanbase/powercontext.git -
Kun
Agents & frameworksLocal-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.
git clone https://github.com/KunAgent/Kun.git -
BioDSH
Agents & frameworksThe bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click installers, a skill store, offline mode.
git clone https://github.com/sagirimo/BioDSH.git -
deerflow-book
Agents & frameworks本书围绕 DeerFlow 2.0,从理论到源码,系统讲解如何进行二次开发。(精校)
git clone https://github.com/hawkli-1994/deerflow-book.git -
open-multi-agent
Agents & frameworksSelf-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
git clone https://github.com/open-multi-agent/open-multi-agent.git -
dsh-auto-review
Agents & frameworksSecond-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
git clone https://github.com/PerryLink/dsh-auto-review.git -
rlcard
Agents & frameworksReinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
git clone https://github.com/datamllab/rlcard.git -
dsh-video-storyboard
Agents & frameworksScene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.
git clone https://github.com/SAOS-3624/dsh-video-storyboard.git -
Proteus
Agents & frameworksSelf-evolution for any agent harness. Plug in. Evolve. Measure.
git clone https://github.com/proteus-evolve/Proteus.git -
codeg
Agents & frameworksCollaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.
git clone https://github.com/spacering-net/codeg.git -
dsh-auto-memory
Agents & frameworksTrustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.
git clone https://github.com/AskTheWay/dsh-auto-memory.git -
dsh-suite
Agents & frameworksThe living DeepSeek Harness plugin directory — refreshed hourly, compat-tested daily, with an in-app plugin store and scaffolder. DSH 插件活目录:每小时刷新,每日兼容实测,内置插件商店与脚手架。
git clone https://github.com/whyihaveyou/dsh-suite.git -
capri-ai-desktop
Agents & frameworksCapri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.
git clone https://github.com/edgerunners-2/capri-ai-desktop.git -
Yuxi
Agents & frameworks可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
git clone https://github.com/xerrors/Yuxi.git -
MemT-1.0
Agents & frameworksOfficial repository for MemT-1.0
git clone https://github.com/MemTensor/MemT-1.0.git -
agy-staff
Agents & frameworksHire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code, OpenAI Codex, and DeepSeek Harness.
git clone https://github.com/keli-wen/agy-staff.git -
harness-mix
Agents & frameworksgit clone https://github.com/emo-xiaoyu/harness-mix.git -
pi-dynamic-workflows
Agents & frameworksClaude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git-worktree isolation, cost accounting, an interactive /workflows TUI, an /ultracode standing opt-in, and deep research.
git clone https://github.com/QuintinShaw/pi-dynamic-workflows.git -
LLM-VM
Agents & frameworksirresponsible innovation. Try now at https://chat.dev/
git clone https://github.com/anarchy-ai/LLM-VM.git -
dsh-permission-rules
Agents & frameworksClaude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
git clone https://github.com/PerryLink/dsh-permission-rules.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.