에이전트 강화
게시자가 제공하는 설치 방식입니다. PlugMCP 엔드포인트가 아닙니다.
원격 URL인가요, 내 컴퓨터에서 실행하는 명령인가요? 두 설치 방식의 차이
PlugMCP에서 실행
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
실행게시자 제공
culi (cà phê culi — the single dense peaberry bean) is the memory and context layer between your coding agents and your projects. It stores rules, lessons, styles, patterns, skills, and agent definitions as small Markdown cards, then routes a token-budgeted selection to Claude Code or Codex.
Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it learns lessons from your sessions. Agent memory + context engineering as a single static Go binary.
It is local-first, git-backed, and inspectable. Hooks and retrieval make no model calls; optional background learning proposes new knowledge for review. No Node, Python, or resident daemon is required.
claude:<id> and
codex:<id> provenance.~/.culi/knowledge/; SQLite holds rebuildable card-search tables
plus preserved local activity state.go install github.com/hung12ct/culi/cmd/culi@latest
culi init # auto-detect Claude Code and Codex
culi serve # http://localhost:7378
Open a new coding-agent session after initialization. Codex users should run /hooks once and
trust the four generated Culi hooks. Verify the wiring with:
culi doctor --harness=codex
Ollama is optional. Without it, retrieval uses SQLite FTS/BM25. For semantic retrieval, install
Ollama and run ollama pull nomic-embed-text.
For harness-specific setup, adding your first cards, and importing existing instructions, see the getting started guide.
The local console makes Culi's behavior visible and reversible: review proposed lessons, search and edit cards, filter delivery activity by agent/repository/date, compare hot cards across Claude and Codex, and safely tune the learning backend.
| Home — health, next actions, and savings | Review — evidence-first lesson decisions |
|---|---|
 |  |
prompt ──► cheap gate ──► scope + keyword + optional semantic retrieval
│
rank + budgeted pack
│
Claude Code or Codex
│
session transcript ──► background mining ──► review ──► knowledge cards
search_context, expand_card, and save_lesson.The default auto provider tries configured APIs first, then signed-in Claude and Codex terminals.
Ollama is opt-in so Culi never silently chooses an unprepared local generation model. Model calls
never occur in prompt hooks.
See learning and cost for Codex backfill, authentication, caps, model defaults, and manual learning commands.
config.yaml reference and safe console settings.Run culi help for the complete command list.
go install (the Go toolchain can download the pinned version automatically).nomic-embed-text is optional.Actively developed and dogfooded daily. Built on gopheragent. Issues and ideas are welcome.
MIT © 2026 hung12ct
Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it
개요
Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it learns lessons from your sessions. Agent memory + context engineering as a single static Go binary.
도구
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
FAQ
이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 stdio 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
이 레코드에는 필수 환경 변수가 등록되어 있지 않습니다.
Culi은(는) stdio를 통해 로컬에서 실행됩니다.
마지막 확인: 2026-10-28. Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it learns lessons from your sessions. Agent memory + context engineering as a single static Go binary.
