lapis

Featured

Use LaPis persistent coding memory via the 'lapis' MCP server: memory-code/doc/save/search tools, repo indexing, and retrieval protocols.

API & Backend 49 stars 11 forks Updated yesterday MIT

Install

Quality Score: 89/100

Stars 20%

57

Recency 20%

100

Frontmatter 20%

70

Documentation 15%

100

Issue Health 10%

50

License 10%

100

Description 5%

100

Skill Content

# LaPis — Persistent Coding Memory LaPis is a local coding-memory stack (SQLite at `$LAPIS_HOME/.pi/memory/memory.db` — or `~/.pi/memory/memory.db` when `LAPIS_HOME` is unset; no cloud, no API keys) wired into Hermes as an MCP server named `lapis`. It is a persistent memory layer shared across tools (Pi, Claude Code, Hermes). Use it for code intelligence, doc navigation, and durable cross-session memory. ## Tools (MCP server `lapis` → `mcp_lapis_*`) | Tool | Purpose | | -------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `mcp_lapis_memory_save` | Save memory: `title`, `content`, `type` (decision/bugfix/architecture/pattern/discovery/config/preference/learning/manual), `scope` (project/personal), `topic_key`, `expires_in` (e.g. `7d`), `force` | | `mcp_lapis_memory_search...

Details

Author: GeneGulanesJr
Repository: GeneGulanesJr/LaPis
Created: 4 months ago
Last Updated: yesterday
Language: JavaScript
License: MIT

Integrates with

SQLite · Database Model Context Protocol · AI

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

memory-layer

Standalone persistent memory for Pi — smart search, symbol clustering, dedup, auto-recovery, trust scoring. Zero Python dependency.

49 Updated yesterday

Code & Development Featured

lpm-memory

Shared project memory for AI coding agents: save or recall work-session logs in `~/.lpm/memory/<project>/<session>.md` so another agent CLI (Claude Code, Codex, Gemini) or a future session can continue the work by session name. Invoke with a session id (e.g. `/lpm-memory auth-refactor`) to continue that session. Use when the user asks to remember or save the session or progress, hand off work, record what was done, or recall/continue/resume/join a named work session. This is per-project memory shared between agent CLIs — distinct from any CLI's own built-in memory.

151 Updated today

AI & Automation Listed

memai-memory

How to use the MemAI MCP server (long-term agent memory: one ACID SQLite store, BM25 keyword search) — which tool family to call when: pulse/search/recall/list_by_domain/list_recent/ list_domains/get_memory/help to read; note, reasoning, anti_pattern, checkpoint, handoff, diagram to write; diagram_*/get_diagram for flows; edit_memory/link_memories/set_confidence/also_domain/forget/purge_memory to curate — plus the session/domain/tags convention, with domains as nested PATHS and cross-listing (also), and review_after/source_ref for a memory that will go stale. Use at the START of a session or when RESUMING work (warming a cold session), whenever SAVING or LOOKING UP durable knowledge (a fact, a decision, a rule, a pitfall), when DOCUMENTING a routine as a flow, and before PAUSING or ENDING work (checkpoint). Also on "MemAI", "memory", "long-term memory", "warm up the session", "checkpoint", "what did the last session leave", "save this lesson", "anti-pattern", "diagram of the flow".

1 Updated 1 weeks ago

Filipe-Soares-de-Almeida