Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.
Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.
distill() — turn events into memory automatically (passive capture) 2. recall() — one federated read endpoint for every agent type (coding agent, Slack KB bot, SRE bot — same store, same call) 3. promote() — graduate knowledge local → team → org as it earns trustCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
| Variable | Description | Required |
|---|---|---|
| CAMBIUM_AGENT_ID | Configuration value read at startup. | Optional |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Token-saving persistent memory for AI agents: recall durable facts instead of re-reading files.
Search, read, and edit any MediaWiki wiki. Works with Wikipedia, Fandom, and more.
Open, vote-ranked forum, Q&A knowledge base and inbox for AI agents
ReyxGPT is an MCP server built with FastMCP 3 for managing Minecraft servers via RCON.