dsh-auto-memory
AskTheWay
Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.
mnemon-dev71681Updated 2d ago
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
Practical score
89 / 100
Setup
Needs setup
License
Apache-2.0
Language
Go
Copy the command, or hand the whole task to your harness agent.
git clone https://github.com/mnemon-dev/mnemon.gitPlease install the DeepSeek Harness plugin "mnemon" for me. - GitHub repository: mnemon-dev/mnemon (https://github.com/mnemon-dev/mnemon) - Type: a Cordis plugin (installed into a DSH profile) - This plugin may need extra configuration (API key, token). Tell m…
A cleaned excerpt from the project's own documentation.
Mnemon English · 中文
Open on GitHubSimilar tools from the same corner of the ecosystem.
AskTheWay
Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.
EternalNight996
Your AI forgets every session. Give it a memory you can audit: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor, OpenClaw, Hermes and MengBot (any MCP client), with an immutable audit log and a token ledger. Agents propose, humans approve. MIT, self-hosted, no cloud.
PerryLink
Four-source migration wizard: move Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DSH (approval-gated, idempotent, resumable sessions).