LycheeMemLycheeMem/LycheeMem
Provides a lightweight long-term memory layer for LLM agents so they remember user preferences,…
No ratings yet
Rate this skill
Stars1.1k
Forks18
Watchers1.1k
Open Issues2
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/LycheeMem/LycheeMem.git
OverviewOverview
Key Features
Provides a lightweight long-term memory layer for LLM agents so they remember user preferences, past conclusions and key facts across sessions instead of starting from scratch each time. Key capabilities include: 1. Long-term memory storage: writes extracted conversation points into a persistent memory store that survives across sessions, avoiding repeated questions for the same information; 2. Memory retrieval and injection: recalls relevant memories at conversation start based on the current question and injects them into context so answers carry historical background; 3. MCP server integration: exposes memory read/write interfaces as an MCP Server that can be mounted directly into MCP-compatible clients and agent frameworks; 4. Plugin-based integration: ships an OpenClaw plugin form that adds memory to existing agent workflows without restructuring existing code; 5. Lightweight context control: recalls only memory fragments relevant to the current task, reducing irrelevant content occupying the context window.
Use Cases
Adding cross-session memory to personal assistant agents, preserving decisions and conclusions in multi-turn project collaboration, mounting a reusable memory service to MCP clients, adding a memory module to OpenClaw agents, compressing and retaining key information in long conversations.
Target Roles
AI / Algorithm Engineer, Backend Developer, Full-stack / Indie Developer, Product Manager (PM).
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 1779 |
|---|---|
| Data source | GitHub |
| Repository | LycheeMem/LycheeMem |
| Category | AI & Agents / Agent Memory & Context Management |
| Primary language | Python |
| License | Apache License 2.0 |
| Default branch | master |
| GitHub repository ID | 1189518533 |
| Node ID | R_kgDORuacxQ |
| Rank | #686 (position within the source ranking) |
| Site-wide popularity rank | #805 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
Still collecting
First record taken on 2026-09-29. Two days of data are needed before a trend line can be drawn.
TimelineTimeline
Repository created2026-03-23 12:01:438 months ago
Data last updated2026-10-26 12:02:3423 days ago
Last commit2026-08-06 14:54:113 months ago