.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/labyrinth-analytics/loreconvo
home/mcp-servers/labyrinth-analytics/loreconvo
labyrinth-analytics avatar

loreconvo

bylabyrinth-analytics· 2 MCP servers

Stars

10

Category

Documentation & Knowledge

View on GitHub

TL;DR

Cross-surface persistent memory for Claude sessions. Vault conversations from Code, Cowork, and Chat -- recall decisions, artifacts, and context in any future session.

How to install loreconvo?

labyrinth-analytics/loreconvo
$git clone https://github.com/labyrinth-analytics/loreconvo

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install loreconvo by running `git clone https://github.com/labyrinth-analytics/loreconvo`, then use it for the current task and follow its documentation at https://github.com/labyrinth-analytics/loreconvo.

Files · 1

View on GitHub
README.md
1# LoreConvo v0.8.5
2 
3Your memory follows your identity, not your tool — with your consent.
4 
5LoreConvo is the only AI memory that carries your context across Claude Code, Codex, Cursor, and Hermes Agent. One install, one memory, everywhere you code.
6 
7> **Available on the Anthropic Marketplace.** Install directly from Claude, or via PyPI: `uvx loreconvo`
8 
9## Why LoreConvo?
10 
11### Works wherever you work
12 
13LoreConvo works across Claude Code, Cursor, Codex, and Hermes -- the same memory
14layer, no matter which client you reach for. When you switch mid-project, your
15context travels with you automatically.
16 
17Most tools wall off memory by machine or workspace. LoreConvo stores everything
18locally in a SQLite database you own, and surfaces it wherever you are. You decide
19what gets saved; nothing is written without your action.
20 
21### You control what gets saved
22 
23Competing tools auto-write to memory without asking. LoreConvo puts you in control: you decide what's worth keeping, and you can delete any memory at any time.
24 
25Every memory shows you exactly where it came from — which surface captured it, when, what project context it belongs to, and which skill generated it. No mystery. Full provenance.
26 
27### Your memory stays on your machine
28 
29LoreConvo stores everything in a SQLite database on your own machine. No data leaves your computer. No cloud accounts. No vendor with access to your session history.
30 
31Your sessions live in `~/.loreconvo/sessions.db` -- a file you own, can back up, and can delete whenever you want.
32 
33### Structured memory, not raw transcripts
34 
35LoreConvo captures two types of memory for each session:
36 
37- **Episodic memory:** what happened -- summaries, artifacts created, open questions left behind
38- **Semantic memory:** what was decided -- stable conclusions about the project that persist across sessions
39 
40Together these give Claude a structured, searchable record of your project's history, not just a pile of chat transcripts.
41 
42## Recall Benchmark
43 
44LoreConvo's FTS5 search is benchmarked against a 60-session synthetic corpus (6 topic areas, 36 labeled queries).
45 
46| Variant | Recall@5 | MRR |
47|---------|----------|-----|
48| FTS5 + compound token expansion (default) | **88.9%** | **0.875** |
49| FTS5 baseline (no expansion) | 72.2% | 0.708 |
50 
51Compound token expansion (camelCase / snake_case query preprocessing) lifts Recall@5 by **+35.7 pp** on queries using technical identifiers like `autoSave`, `pipeline_tracker`, and `get_context_for`.
52 
53[Full benchmark report](docs/agent-reports/benchmarks/loreconvo_recall_benchmark_20260522.md) |
54[Reproduce](scripts/run_loreconvo_recall_benchmark.py)
55 
56## Quick Start
57 
58One command to install:
59 
60```bash
61bash install.sh
62```
63 
64This creates a virtual environment, installs dependencies, and verifies everything works. No system Python changes, no manual pip commands.
65 
66## Using LoreConvo
67 
68### Claude Code (Terminal)
69 
70**Start a session with the plugin loaded:**
71 
72```bash
73claude --plugin-dir /path/to/loreconvo
74```
75 
76**Or load it inside an existing session:**
77 
78```
79/plugin add /path/to/loreconvo
80```
81 
82Replace `/path/to/loreconvo` with wherever you saved the source folder.
83 
84After making code changes, use `/reload-plugins` to refresh without restarting.
85 
86Once loaded, Claude has access to all 28 LoreConvo MCP tools automatically. Ask Claude to "save this session" or "recall what we discussed about X" and it will use the tools on its own.
87 
88### Cowork (Desktop App)
89 
901. Click the **+** button next to the prompt box
912. Select **Plugins**
923. Select **Add plugin**
934. Browse to the `loreconvo` source folder
94 
95**Important: Shared Database Access**
96 
97Cowork runs in a sandboxed VM and can't see your Mac's filesystem by default. To read sessions saved by Claude Code, ask Claude in Cowork:
98 
99> "Mount my ~/.loreconvo folder"
100 
101Once mounted, Cowork reads and writes to the same database as Claude Code. Sessions saved in Code appear instantly in Cowork.
102 
103### Claude Chat (Web)
104 
105Chat doesn't support plugins, so LoreConvo provides a one-command bridge. Run this in your terminal:
106 
107```bash
108bash export-to-chat.sh
109```
110 
111This exports your last session and copies it to your clipboard (macOS). Switch to Chat and paste (Cmd+V). Chat instantly has the context from your Code or Cowork session.
112 
113To search for a specific session:
114 
115```bash
116bash export-to-chat.sh "tax prep"
117```
118 
119## How It Works Across Surfaces
120 
121The core value of LoreConvo is that context persists across Claude surfaces automatically. Here is the full chain:
122 
123```
124Claude Code (~/.claude/settings.json via `claude mcp add`)
125 |-- SessionEnd hook --> auto_save.py --> ~/.loreconvo/sessions.db
126 |-- SessionStart hook <-- auto_load.py <-+
127 |
128Cursor (.cursor/mcp.json) <--MCP-----+
129Codex (~/.codex/config.toml) <--MCP-+
130Hermes Agent (~/.hermes/config.yaml) <-MCP-+
131 All surfaces: save_session / get_recent_sessions / search_sessions
132 
133Claude Chat (web)
134 |-- export-to-chat.sh --> clipboard --> paste into Chat
135```
136 
137**Claude Code** is

Preview

labyrinth-analytics/loreconvolabyrinth-analytics/loreconvo
Repolabyrinth-analytics/loreconvo
TypeMCP Servers
CategoryDocumentation & Knowledge
UpdatedJul 2026
LicenseNOASSERTION
First seenJul 27, 2026

Tags

MCP

Related

6 picks
Type
  1. upstash avatarContext7Up-to-date library docs injected straight into your promptsMCP Serverstoday3.8M60k
  2. yamadashy avatarrepomixA tool to pack repository contents to single file for AI consumptionMCP ServersJul 2026310k27k
  3. trsdn avatarmarkitdown-mcpA Model Context Protocol server for converting documents to Markdown using MarkItDownMCP ServersJun 2026151k29
  4. anyproto avataranytype-mcpOfficial MCP server for Anytype API - your encrypted, local and collaborative wiki.MCP ServersJul 202669k487
  5. aashari avatarmcp-server-atlassian-confluenceNode.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.MCP ServersFeb 202623k60
  6. boweylou avatarobsidian-mcp-server-enhancedThis is an enhanced version of the excellent cyanheads/obsidian-mcp-server with additional features specifically tailored for remote Claude.ai integration, advanced task querying, and security via Tailscale.MCP ServersJul 202617k32