IHMT Memory gives long-term memory to AI coding agents including Claude Code, Codex and opencode, structured as a tree of plain files. Memory lives in your repository as readable files rather than in a database the agent cannot show you.
Be the first to rate IHMT Memory. Your feedback helps other users decide.
Keep decisions and conventions available to the agent next week.
Read and diff the memory tree yourself instead of trusting a black box.
Share the same tree between Claude Code, Codex and opencode.
Similar tools in the same category — compare side-by-side
Agent Chrome Relay lets your coding agents, including Claude Code, Codex, Cursor, Paseo and pi, use ...
Endo is the Higher Order Harness: a unified chat interface that composes any agent, on the subscript...
0sql is an open source semantic layer that returns SQL rather than answering questions itself. You m...
Guides and comparisons about code tools
Ten Show HN projects for running several agents at once: orchestrators, subagents in isolated worktrees, shared memory trees and browser relays.
Nine Show HN launches beneath the model: filesystems, snapshots, gateways and deploy tools that decide what an agent sees and what survives.
Nine launches that check agent work: per-call access policy, MCP server vetting, runtime verification, readable diffs and a hard stop at 95%.
Nine Show HN launches sitting under the agent: a model gateway, vectorless retrieval, on-device inference, an MCP browser layer and connectors for real systems.
Eight Show HN projects for trusting long agent runs: work context capture, distilled memory, folder fences, dollar budgets, plan review and tool governance.
