Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
dapr-agents
Agents & frameworksBuild durable, autonomous, resilient and observable AI agents with built-in workflow orchestration, security, statefulness and telemetry.
git clone https://github.com/dapr/dapr-agents.git -
python
Agents & frameworksOpen-source Python challenge courses — your AI coding agent teaches, verify.py decides when you're done.
git clone https://github.com/flypythoncom/python.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 -
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 -
Hycli
Agents & frameworksWebsites, ready for AI. Turn website tasks into verified CLI and MCP actions, with a local dashboard and 20 languages.
git clone https://github.com/Hybirdss/Hycli.git -
Revia
Agents & frameworksAgent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs.
git clone https://github.com/regrevia/Revia.git -
BambooAI
Agents & frameworksAI-powered data analysis workbench built for transparency, reproducibility and user control. Inspect the code and evidence behind results, verify calculations through replay, and choose from a wide range of models, including local open-weight models.
git clone https://github.com/pgalko/BambooAI.git -
spec-harness
Agents & frameworks面向 AI 编程智能体的任务包工作流工具,用可验证的范围、证据和 Git 门禁管理长期改动。(Task-package workflow for AI coding agents with verifiable scope, evidence, and Git gates.)
git clone https://github.com/MicTx/spec-harness.git -
Meta_Kim
Agents & frameworksGoverned execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.
git clone https://github.com/KimYx0207/Meta_Kim.git -
bernstein
Agents & frameworksThe open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
git clone https://github.com/sipyourdrink-ltd/bernstein.git -
Verovo
Agents & frameworksAI financial audit and task economics: connect usage, supplier charges and business outcomes to calculate task costs, cost per verified success and ROI.
git clone https://github.com/roy-tong/Verovo.git -
opendraft
Agents & frameworksThe open-source agent system that writes research papers with verified citations. Every citation checked against Crossref, OpenAlex and Semantic Scholar.
git clone https://github.com/federicodeponte/opendraft.git -
awsl
Agents & frameworksCodex-verified, Claude-compatible durable local runtime for Claude Code Workflow JS, with resume, checkpoints, budgets, and Git worktrees
git clone https://github.com/XhinLiang/awsl.git -
openkakao-cli
Agents & frameworksKakaoTalk CLI for macOS and AI agents: send, read, react, search, back up and clean up chats through the official app. Login-free, verified sends in 0.5 s.
git clone https://github.com/JungHoonGhae/openkakao-cli.git -
loop.js
Agents & frameworksA loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
git clone https://github.com/loop-js/loop.js.git -
Agentlas-OS
Agents & frameworksThe Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor.
git clone https://github.com/agentlas-ai/Agentlas-OS.git -
embodied-first-exam
Agents & frameworksThe first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
git clone https://github.com/mll-lab-nu/embodied-first-exam.git -
asqav-sdk
Agents & frameworksPython and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.
git clone https://github.com/jagmarques/asqav-sdk.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 -
agency-orchestrator
Agents & frameworks🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队,几分钟交付完整方案;验收自动核验,网页 / 桌面 / Docker 全渠道。
git clone https://github.com/jnMetaCode/agency-orchestrator.git -
opus-manager
Agents & frameworksMake Claude the manager, not the coder: one skill that hands work to cheaper AI CLIs, verifies the results, and gets a second vendor to review.
git clone https://github.com/yanauto/opus-manager.git -
ordewell
Agents & frameworksMulti-agent task orchestration for coding agents. Turn one goal into an ordered plan of tasks (each with its own runner, model and mode), then execute and verify the results.
git clone https://github.com/ordewell/ordewell.git -
Cohort
Agents & frameworksLocal-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory.
git clone https://github.com/congchuanling-dot/Cohort.git -
walrus-memory
Agents & frameworksA portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.
git clone https://github.com/MystenLabs/walrus-memory.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.