Engraphy

Purpose: Giving AI agents persistent associative memory instead of relying only on short-lived conversation context.

Inferred · not functionally tested

Audience: AI developers building agents and MCP-based applications

Inferred · not functionally tested

Functions: agents, rag

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: commercial_oss · license: Open Source · platforms: WEB · deployment: browser, self_hosted, cli, api_only

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: github.com. These links do not verify the individual claims.

Engraphy is a Memory & skills project. Inferred · not functionally tested: It focuses on giving AI agents persistent associative memory instead of relying only on short-lived conversation context. Inferred · not functionally tested: Engraphy is an open-source project aimed at AI developers building agents and MCP-based applications. Basis unknown · not verified: It follows a commercial open-source model under the Open Source license. Basis unknown · not verified: It runs on the web, the command line, and API, and it can be self-hosted.

Behind Engraphy is Devon Clark. Inferred · not functionally tested: Key capabilities include associative memory, typed graph, and postgres backend. Inferred · not functionally tested: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.