One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
- agentic-ai
- ai
- chats
- llm
47,133 repositories indexed
1–9 of 9 · Most stars
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
TranslatedNot a Q&A bot, but a digital twin that can actually get work done. Agents and project context are shared, so all project members can work together. At the same time, agents, like people, abstract and summarize experience from materials or work into the project context.
TranslatedOpen-source GrokBot alternative built on DeepSeek Harness. Build your personal bot team: multiple personal agents with persistent memory, identities and permissions, extensible through DSH plugins. MIT.
TranslatedGive your AI a body, and a bit of human touch — a QQ companion chatbot that remembers things and reads the occasion, plus an MCP server that can control Android phones
Official repository for MemT-1.0
Translated🐋 DSH Fish Memory: gives sessions a long-term memory that fades over time, with a timestamp on every entry. The "fish" in the name comes from DeepSeek's whale.
TranslatedMulti-scenario AI workbench: six-layer master outline + topology wiring diagram + public-version workbench templates (four scenarios can run, source code can be copied and used as is) + memory mechanism. Companion marketplace: https://www.mydsh.xyz . Author: https://linyujia.me . Note: it does not work as soon as it is installed; the scenarios need to be tuned to your own content.