AgentPostmortem
Organization@agentpostmortem
A public registry of documented AI-agent failures, plus the verification, eval, and security tooling built from it.
4
Published Tools
1
Total Stars
9
Weekly Downloads
3
GitHub Followers
22
Public Repos
Published Tools
2 MCP Servers1 Skill1 Agentacross 3 categoriesAgentPostmortem
A remote MCP server that turns AgentPostmortem, a public registry of documented AI-agent failures, into tools any agent can query. Ships with a companion investigator agent that drafts postmortems grounded in real precedents.
...moreroyalpinto007
A security scanner and linter for Model Context Protocol (MCP) servers. Like npm audit / eslint, but for MCP.
Observability for Claude Code subagents. Parses session transcripts, surfaces what agents actually did, and flags the failure patterns.
...morePermission-aware RAG: access control enforced in the retrieval query, not after it.