PyPI · Go · npm
preloop/preloop
The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observability, and audit trails
Apache-2.02026年9月18日 · 指标 2.10.0
全部标签
目录标签
#human-in-the-loop
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
55 条记录
Go · npm
dagucloud/dagu
Self-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler.
GPL-3.02026年9月20日 · 指标 2.10.0
PyPI · Go · npm
cordum-io/cordum
The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
自定义许可证2026年9月17日 · 指标 2.10.0
npm
node9-ai/node9-proxy
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
Apache-2.02026年9月13日 · 指标 2.10.0
npm · Go
tokencanopy/e2a
Open-source email API for applications and AI agents. Managed hosting at e2a.dev, or self-host with Docker.
Apache-2.02026年9月11日 · 指标 2.10.0
npm · Go
humanlayer/humanlayer
The best way to get AI coding agents to solve hard problems in complex codebases.
自定义许可证2026年10月17日 · 指标 2.10.0
npm · crates.io
smithersai/smithers
Smithers is an agentic workflow framework for defining workflows in simple TypeScript configuration files and executing them quickly, durably, and reliably
MIT2026年9月11日 · 指标 2.10.0
npm
emiliaprotocol/emilia-protocol
Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.
Apache-2.02026年10月22日 · 指标 2.10.0
crates.io · npm
frumu-ai/tandem
Tandem is the authority layer between AI agents and company tools: runtime policy for tools, memory, approvals, and audit trails.
自定义许可证2026年9月8日 · 指标 2.10.0
npm
maxritter/qualitylayer
Plan, build and review software with your coding agents. Work side by side in the App or browser, or use your favourite terminal or IDE.
自定义许可证2026年10月22日 · 指标 2.10.0
npm
lua-ai-global/governance
Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
MIT2026年9月13日 · 指标 2.10.0
npm
Protocol-Wealth/pwos-core
Open source compliance-first AI operating system for SEC-registered investment advisers. Apache 2.0 licensed with defensive patent grant.
Apache-2.02026年9月13日 · 指标 2.10.0
npm
egeominotti/bunqueue
⚡ High-performance job queue for Bun. SQLite by default, PostgreSQL multi-broker when you scale. DLQ, cron, SQLite S3 backups, and native MCP. No Redis.
MIT2026年9月10日 · 指标 2.10.0
Hex
sagents-ai/sagents
Build interactive AI agents in Elixir with OTP supervision, middleware composition, human-in-the-loop approvals, sub-agent delegation, and real-time Phoenix LiveView integration. Built on LangChain.
自定义许可证2026年9月9日 · 指标 2.10.0
PyPI
tuliplabs-ai/tulip-agents
The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already have.
Apache-2.02026年10月8日 · 指标 2.10.0
npm
unmodeled-tyler/vessel-browser
Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP control, and BYOK with full autonomous browsing. Use with Hermes Agent, OpenClaw, or connect to your favorite API provider.
MIT2026年9月12日 · 指标 2.10.0
Packagist
fissible/verdict
A Laravel security boundary for AI-triggered application actions. It bounds what an agent may do — authority, duplication, rate, approval — not what it was trying to do.
MIT2026年10月21日 · 指标 2.10.0
Go · npm
inspr-at/paimos
Self-hosted project context for people and AI agents: specifications, repository knowledge, execution choices, and run evidence in one inspectable history.
AGPL-3.02026年9月11日 · 指标 2.10.0
npm
jagreehal/awaitly
Typed async workflows with Result types and automatic error inference
MIT2026年9月15日 · 指标 2.10.0
npm
ni-c/mcp-approval
Ask a human before your MCP tool does something irreversible — elicitation on both protocol revisions, with a two-call confirmation token for clients that cannot be asked
MIT2026年10月15日 · 指标 2.10.0
PyPI · npm
Stahl-G/briefloop
本地多运行时 Agent 工作台：围绕材料研究、生成可编辑报告、独立复核、追溯证据，并从人工反馈持续学习。
MIT2026年10月11日 · 指标 2.10.0
npm
busabase/busabase
Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human-reviewed changes. Local-first and self-hostable.
MIT2026年9月9日 · 指标 2.10.0
Go
scottames/thts
CLI to manage persistent thoughts and notes across repositories, with AI coding agent integration.
Apache-2.02026年9月14日 · 指标 2.10.0
npm
sensigo-hq/realm
Open-source workflow engine for AI agents. An agent calls Realm over MCP, or realm agent drives a model from the CLI. Steps run in order, agent answers are checked against the schema a step declares, human gates pause the run until answered, and each finished step is recorded.
自定义许可证2026年10月21日 · 指标 2.10.0
Go
23min/aiwf
aiwf is a Git-native kernel for human+AI projects: plans, decisions, and provenance, gated and validated at every commit.
Apache-2.02026年9月13日 · 指标 2.10.0
PyPI
Blockether/vis
Vis is a coding agent that combines tools into Python programs. It can chain operations, run them in parallel, and inspect results before deciding what belongs in the conversation.
Apache-2.02026年9月23日 · 指标 2.10.0
PyPI
forge-play/Forge
The Forge — the engine that refuses a confident wrong answer. Checkpoint loop + measuring panel + calibration for SAFE-native app building.
Apache-2.02026年9月30日 · 指标 2.10.0
npm
generacy-ai/agency
该仓库未发布描述。
Apache-2.02026年9月15日 · 指标 2.10.0
npm
Tiledesk/tiledesk-server
Tiledesk Server is the main API component of the Tiledesk platform 🚀 Tiledesk is an open-source alternative to Voiceflow, allowing you to build advanced LLM-powered agents with easy human-in-the-loop (HITL) when necessary.
MIT2026年7月20日 · 指标 2.10.0
npm
rhanka/h2a
该仓库未发布描述。
MIT2026年9月10日 · 指标 2.10.0