Jev in production › Agent context and memory

MemSearch (Zilliz)

Zilliz's memory layer for coding agents optionally sends each query's ten candidate memories to Jev as independent yes/no questions and sorts by probability; Recall@5 rose 4.70 percentage points over the frozen order on 4,344 queries (company).

Open on GitHub ↗

4.70 percentage pointsmeasured against a baseline, as published by the source
Use
Agent context and memory
Industry
Developer tools
Form
Open-source tool
Stage
In production
Plugs into
Claude Code, Codex, DeepSeek Harness, OpenClaw, OpenCode
Listed
2026-09-22
Found via
github
Repository
zilliztech/memsearch
Stars
2,736
Forks
266
Last push
2026-10-09
Language
Python
License
MIT

The README opens with

- Optional Jev reranking — rerank memory search results with Jev through the TypeSafe API, with no local model download. See configuration and the Chinese/English evaluation.

- DeepSeek Harness support — MemSearch now brings automatic capture, pre-step memory injection, native skill-based recall, background maintenance, and a read-only memory browser to DeepSeek Harness (DSH). - Skills from memory — MemSearch now distills the workflows you repeat into reusable, installable agent skills (a third "procedural memory" layer) and keeps them up to date in the background. See Skills from Memory. - Advanced memory maintenance — optional background tasks keep durable PROJECT.md and USER.md notes current across sessions. See Advanced Memory Maintenance.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent context and memory