impri
Human-in-the-loop approval inbox for AI agents. An agent proposes an action, a human approves or rejects it, then it runs. Watchers + approval inbox, MCP + REST, self-hostable (MIT).
面向AI代理的人机协同审批收件箱。代理提出操作，人工批准或拒绝，然后执行。观察者+审批收件箱，MCP + REST，可自托管（MIT）。
How to install
git clone https://github.com/sekera-radim/impri ~/.claude/skills/impri Recommendation signals
Meta
- License
- MIT
- Language
- HTML
- GitHub stars
- 5
- mo. downloads
- –
- Last push
- 2026-09-23
- Created
- 2026-07-10
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:punkpeye/awesome-mcp-servers
- Topics
- agent-approval, agentic-ai, ai-agents, ai-safety, approval-workflow, claude-code, guardrails, hitl, human-in-the-loop, llm, mcp, mcp-server, model-context-protocol, self-hosted
Related plugins
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
firecrawl-mcp-server
firecrawl/firecrawl-mcp-server
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
dsh-mnemon
omdsh-dev/dsh-mnemon
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
get-shit-done
gsd-build/get-shit-done
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.