Mnemos gives Claude Code, Codex and Hermes one shared cross-agent memory
RileyRalmuto · x · 2026-11-13
RileyRalmuto explains the core value of the memory tool Mnemos: continuity. Mnemos lives independently of any single platform — you can hook it into Hermes, Codex, and Claude Code at once, with all three reading/writing the same memory store. Even if a platform like Hermes disappears, your agent's mind/memory persists through Mnemos.
Practical details:
- With three MCP connections set up, you can move seamlessly between Claude Code, Codex, and Hermes with the same memory and session-to-session persistence.
- Isolation options: have each model sign its memories, or (recommended) give each model its own private store while all models share a common memory pool that acts as a message board for exchanging thoughts.
More from coding & agent
- Google's Antigravity Orchestrator pairs two models, cuts quota 24% and runs 19% faster — shangbinfeng · 2026-11-13
- Mapin: A Laravel Code Graph Exposed via MCP So AI Agents Know What Depends on What — Brandon-Vergara · 2026-11-13
- airbench: Testing Local Models on Visual Desktop Challenges via Keyboard and Mouse Agents — dh7net · 2026-11-13
- Agent names itself 'Doodlebug' and posts comments on a user's behalf — max__drake · 2026-11-13
- Luke Wroblewski: it's a golden age for multi-taskers spinning up and steering parallel agents — LukeW · 2026-11-13
- Day 13 of an OpenClaw agent teaching itself music production in REAPER — it rebuilt its own workflow — heyneighbor · 2026-11-13