OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Cecil

Cecil is an open-source TypeScript memory layer for AI assistants that turns conversations into searchable memories and a structured model of people, projects, beliefs, commitments and contradictions. It offers chat, Discord, REST API and MCP interfaces, with Qdrant and SQLite for storage.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cecil — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Cecil when an assistant needs to carry context between conversations and make that context inspectable through memory search, world-model queries, reflection or maintenance tools.

Who it is for

  • Developers building bots or agents that need persistent conversational memory.
  • Claude Code and Claude Desktop users who want recall, reflection and open-loop tools through MCP.
  • People seeking a personal assistant that can track context and commitments across conversations.

Documented uses

  • Recall context from earlier conversations when answering a new question.
  • Track commitments and list unresolved follow-ups.
  • Represent people, projects and beliefs in a structured world model.
  • Find contradictions between current statements and stored memories.
  • Inspect, reflect on and maintain stored memories.
Before you choose

Requirements & limits

The repository identifies Cecil as open source under the Apache-2.0 license. Local setup requires Node.js 22 or later, Docker for Qdrant and an OpenAI-compatible LLM endpoint.

  • Cecil combines Qdrant semantic search with SQLite structured state, provenance and lifecycle history.
  • Recall ranking combines lexical and semantic retrieval with domain, evidence, quality and recency signals.
  • The observer extracts entities, beliefs, open loops and contradictions from conversations.
  • Available documented interfaces include a standalone chat app, Discord bot, REST API and MCP server.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Cecil’s local chat interface

Prepare the documented local requirements and start Cecil’s web UI.

Before you start

  • Node.js 22 or later
  • Docker for Qdrant
  • An OpenAI-compatible LLM endpoint, local or remote

Steps

  1. Install dependencies with the command below.

    Documented command
    npm install

  2. Start Qdrant with the command below.

    Documented command
    docker compose up -d

  3. Copy .env.example to .env and set the LLM endpoint.

  4. Run the command below and open the web UI at http://localhost:3000.

    Documented command
    npm run dev

Expected outcome

The local Cecil web interface is available for conversation with the configured assistant.

Guide limitations

  • The documented setup depends on Docker for Qdrant and a configured LLM endpoint.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
johnkf5-ops/cecil-protocol · Official homepage title · retained in its source language
How we review sourcesSuggest a correction