loreconvoCAUTION
Cross-surface persistent memory for AI sessions
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Your memory follows your identity, not your tool — with your consent.
LoreConvo is the only AI memory that carries your context across Claude Code, Cowork, Codex, Cursor, and Hermes Agent. One install, one memory, everywhere you code.
Install directly from Claude Code's plugin marketplace, or via PyPI: uvx --from loreconvo[server] loreconvoWhy LoreConvo?
Works wherever you work
LoreConvo works across Claude Code, Cowork, Cursor, Codex, and Hermes -- the same memory layer, no matter which client you reach for. When you switch mid-project, your context travels with you automatically.
Most tools wall off memory by machine or workspace. LoreConvo stores everything locally in a SQLite database you own, and surfaces it wherever you are. Capture happens two ways: explicitly via the save tools, or automatically at session end if you install the optional hooks. Either way, you can inspect, edit, or delete any memory at any time.
You control what gets saved
LoreConvo puts you in control: automatic capture only runs if you choose to install the session hooks, every save is inspectable, and you can delete any memory at any time.
Every 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.
Your memory stays on your machine
LoreConvo stores everything in a SQLite database on your own machine. Your data stays local unless you explicitly enable the optional AI summarization feature (Pro, off by default), which sends a transcript excerpt to the Anthropic API using your own key. No cloud accounts. No vendor with access to your session history.
Your sessions live in ~/.loreconvo/sessions.db -- a file you own, can back up, and can delete whenever you want.
Structured memory, not raw transcripts
LoreConvo captures two types of memory for each session:
- Episodic memory: what happened -- summaries, artifa
21a18892de6fOBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add loreconvo --env LORECONVO_PRO=${LORECONVO_PRO} -- uvx loreconvo==0.10.12Exposed tools (40)
26 read · 12 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
configure_agent_context | write | Store or update a named topic configuration for an agent. |
consolidate_memories | write | Run memory consolidation for a project to build a structured digest. |
create_project | write | Create or update a project definition. |
export_for_anthropic | read | Export LoreConvo sessions to Anthropic managed-agents memory format. Pro only. |
export_sessions | read | Export portable session records to JSON or JSONL for migration. |
get_anti_patterns | read | Retrieve sessions marked as anti-patterns. |
get_context_for | read | Get relevant session context for a topic. |
get_docs_for_session | read | Return LoreDocs documents cross-linked to a LoreConvo session. Pro tier only. |
get_dream_log | read | Return recent consolidation log entries for transparency and diagnostics. |
get_memory_digest | read | Retrieve the current memory digest for a project without re-running consolidation. |
get_project | read | Get project details including recent sessions and skill usage stats. |
get_recent_sessions | read | Get recent session summaries. |
get_related_sessions | read | Find sessions related to a given session by co-occurrence and embedding. Pro only. |
get_server_info | read | Return MCP compatibility status for this LoreConvo server. |
get_session | read | Get full details of a specific session. |
get_skill_history | read | Get all sessions that used a specific skill. |
get_stats | read | Return a usage dashboard: session counts by surface, project, and tag; |
get_tier | read | Return the current LoreConvo license tier and status. |
graph_session_map | read | Render a Mermaid knowledge-graph neighborhood around a session or project. |
import_sessions | write | Import sessions from a LoreConvo export file (JSON or JSONL). |
inject_agent_context | write | Return targeted session context for an agent at session start. |
inspect_sessions | read | Inspect stored sessions: list, filter, or get full detail for one session. |
link_sessions | read | Link two related sessions. |
list_projects | read | List all defined projects with session counts. |
loreconvo_onboard | write | Set up or update your LoreConvo workspace configuration. |
pin_session | read | Pin or unpin a session to exclude it from automated cleanup. |
query_memory_items | read | Query structured memory items by type, project, status, and recency. |
rebuild_index | read | Rebuild the LanceDB semantic search index from all stored sessions. Pro only. |
save_memory_item | write | Save a structured memory item: a decision, open question, or artifact. |
save_session | write | Save a session summary to persistent memory. |
search_sessions | read | Search session memory by keyword, with optional filters. |
session_link_doc | write | Create a manual cross-product link from a LoreConvo session to a LoreDocs doc. |
set_session_expiry | destructive | Set or clear an expiry date on a session. |
tag_as_anti_pattern | read | Mark an existing session as an anti-pattern. Idempotent. |
tag_session | read | Tag a session with a persona for filtered recall. |
transition_memory_item | write | Move a memory item through its lifecycle. |
untag_anti_pattern | destructive | Remove an anti-pattern tag from a session. Idempotent. |
update_memory_item | write | Correct a memory item |
vault_set_tier | write | Activate a tier (free or pro) for LoreConvo. |
vault_suggest | read | Get proactive context suggestions based on your session history. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (4 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (8)
return importlib.import_module(f"loreconvo.core.{module}")set_session_expiry, untag_anti_pattern
.runtime-pin
digest = hashlib.md5(path.encode("utf-8")).hexdigest()sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../src'))
raw = base64.b64decode(_LAB_PUBLIC_KEY_B64)
- **Team memory (Pro):** share session history with teammates -- export sessions to JSON, teammates import with `python -m loreconvo.cli merge` (no server required)
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass.
21a18892de6ffull audit observations/trust-audit/mcp-server/labyrinth-analytics__loreconvo.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 21a18892de6f | CAUTION | B | 89 | first audit |
Questions
What is the loreconvo MCP server?
Cross-surface persistent memory for AI sessions
What tools does loreconvo expose?
40 in total: 26 read-only, 12 that write, and 2 that can delete or overwrite (set_session_expiry, untag_anti_pattern). Every one is listed on this page with its risk.
Is loreconvo safe to connect to an agent?
With care. The audit graded it B (89/100) and found 8 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does loreconvo need?
It reads ANTHROPIC_API_KEY, LORECONVO_ANTHROPIC_API_KEY, LORECONVO_AUTO_LOAD_MAX_TOKENS and LORECONVO_PRO from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does loreconvo run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as loreconvo.
How current is this page?
The grade is for one exact copy of the source (21a18892de6f), read on 2026-10-10. The repository is watched and re-audited when it changes.