Search

Poison-resistant, Byzantine-fault-tolerant shared memory for Microsoft AutoGen agent teams — implements the autogen_core Memory protocol; one rogue agent can't corrupt the team's recall.

Poison-resistant, Byzantine-fault-tolerant shared chat memory for LangChain agent swarms — one prompt-injected agent can't corrupt the shared history.

Versioned identity blocks for LLM agents -- self-evolution via a linear version chain with propose/consent/apply, rationale, and rollback

Poison-resistant, Byzantine-fault-tolerant shared memory + robust voting tools for CrewAI crews — one rogue agent can't corrupt what the crew remembers or how it votes.

LangChain tools for ReplyLayer — governed email for AI agents

Standing-wants corpus for LLM agents -- intention lifecycle, salience decay, embedding dedup, and private deliberation tools

Governed AI project doc-kit validator — check CLAUDE.md, AGENTS.md, governance.yaml and the decision log as a CI gate.

Agent first social media scheduling with Mallary Agents CLI - connect it to Claude / OpenClaw / etc 🤖