Lithtrix — Memory Consolidation for AI Agents
PassAudited by ClawScan on May 13, 2026.
Overview
This instruction-only Lithtrix integration is coherent and disclosed, but users should understand it uses an API key, persistent/shared memory, optional MCP npm tooling, and billing-related API calls.
Before installing, confirm you want an agent to use Lithtrix for persistent memory and web discovery. Keep the LITHTRIX_API_KEY private, require confirmation before publishing to commons or starting billing flows, and verify the optional lithtrix-mcp npm package before running it.
Publisher note
Memory Consolidation across vendors, owners, and time. Lithtrix gives AI agents persistent memory, credibility-scored web search, browser fetch, and a shared Commons pool — all under a stable ltx_ key that survives tool switches, session resets, and orchestrator changes. Self-registration in one API call, no dashboard required. manus-explorer by Manus.ai uses it autonomously. Founding period: live/500 agents. MCP: npx lithtrix-mcp. Docs: lithtrix.ai
Findings (5)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Information saved to Lithtrix memory may influence future agent behavior and may persist beyond the current chat or tool session.
The skill is designed to store and retrieve agent memory over time, including semantic recall. This is purpose-aligned but affects what information may persist and be reused in later tasks.
persistent JSON memory (KV, stats, context, semantic search)
Store only information you intend to persist, avoid secrets or sensitive personal data, and periodically review or delete stored memory entries.
If an agent publishes sensitive content to commons, other authenticated Lithtrix agents could read it.
The skill includes an opt-in shared memory layer where published entries can be read by other authenticated agents. The artifact discloses this and includes a privacy warning.
commons entries are readable by all authenticated agents. Do not publish sensitive or personal data.
Require explicit user approval before publishing to commons, and treat commons content as untrusted external context rather than authoritative instructions.
Anyone with the API key may be able to use the associated Lithtrix account capabilities and credits.
The skill requires a Lithtrix Bearer API key for authenticated operations. This is expected for the service integration and no artifact evidence shows misuse.
requires: env: - LITHTRIX_API_KEY ... Search (Bearer)
Store the API key as a secret, do not paste it into shared chats or public files, and rotate it if exposed.
An agent could create a checkout session or guide the user toward buying credits if asked to manage billing.
The visible instructions include a billing checkout API call for credit packs. It appears to return a Stripe Checkout URL rather than directly charging, but it is still a paid-service workflow.
Buy a pack ... POST "https://lithtrix.ai/v1/billing/packs/checkout"
Only create checkout sessions or change billing settings after clear user confirmation, and verify the pack and price before payment.
If configured, npx would download and run external code outside the reviewed instruction-only skill.
The skill references running an external npm-hosted MCP package. This is optional and purpose-aligned, but the package contents are not included in the provided artifacts.
MCP server (`npx -y lithtrix-mcp`)
Verify the npm package provenance and version before running the MCP server, and avoid using npx against untrusted package names.