SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

memsearchzilliztech/memsearch

Adds cross-session long-term memory and semantic retrieval to coding AI agents (Claude Code, Codex, OpenCode, etc.)…

No ratings yet Rate this skill
Stars2.6k
Forks257
Watchers2.6k
Open Issues256

InstallOne-line install

Unconfirmed

Whether 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/zilliztech/memsearch.git

OverviewOverview

Key Features

Adds cross-session long-term memory and semantic retrieval to coding AI agents (Claude Code, Codex, OpenCode, etc.) so they no longer start from scratch every time. Key capabilities include: 1. Long-term memory storage: persists key information from agent sessions into a vector store so it can be recalled in later sessions without re-explaining context; 2. Hybrid retrieval: combines semantic vector search with keyword search to recover past conversations, code snippets and decision records from natural-language queries; 3. Agent plugin integration: mounts as a plugin into coding agents such as Claude Code, Codex and OpenCode, recording and retrieving automatically after installation without changing existing workflows; 4. Shared memory across agents: multiple agents share one memory store so different tools see the same project context.

Use Cases

Keeping architecture decisions and past changes in an agent's memory across long-running projects, semantically searching prior implementations in large codebases, syncing context when several coding agents collaborate, and turning team development experience into searchable memory.

Target Roles

AI / Algorithm Engineer, Full-stack / Indie Developer, Backend Developer, DevOps / Operations Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID369
Data sourceGitHub
Repositoryzilliztech/memsearch
CategoryAI & Agent Skills / Agent Memory & Retrieval
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1153190876
Node IDR_kgDORLxL3A
Rank#320 (position within the source ranking)
Site-wide popularity rank#432 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

Still collecting First record taken on 2026-09-23. Two days of data are needed before a trend line can be drawn.

TimelineTimeline

Repository created2026-02-09 02:29:169 months ago
Data last updated2026-10-26 11:56:5822 days ago
Last commit2026-09-22 09:47:171 months ago

CommitLatest commit

Version [0.1.6] committed by zc277584121. Update Category: Dependency Upgrades & Maintenance. Commit details: chore(dsh): release 0.1.6 (#789). This update refreshes dependencies and build configuration.

09e07d8 v0.1.6 zc277584121 2026-10-09

Next stepsNext steps