Give Codex a private, local memory without filling every prompt with your history:

codex mcp add synapse -- uvx --from synapse-vault synapse mcp --vault /absolute/path/to/my-brain

Nothing from the vault is injected into the agent's prompt. The agent searches first, then reads one relevant Markdown page. A thousand unopened pages cost zero tokens.

See it in ten seconds

uvx --from synapse-vault synapse serve --demo

That opens a populated 20-page graph. It needs no API key, import, database server, or JavaScript build.

Keep your own history

uvx --from synapse-vault synapse init ./my-brain
uvx --from synapse-vault synapse ingest ~/Downloads/chatgpt-export --vault ./my-brain
uvx --from synapse-vault synapse serve --vault ./my-brain

Ingest is local and free: it writes Markdown and builds a disposable SQLite FTS5 index. Search works immediately:

uvx --from synapse-vault synapse search "the phrase I remember" --vault ./my-brain

To turn raw history into a linked wiki, estimate first and then build a small resumable batch:

export SYNAPSE_API_KEY="..."
uvx --from synapse-vault synapse build --vault ./my-brain --limit 20 --dry-run
uvx --from synapse-vault synapse build --vault ./my-brain --limit 20

The build pass is optional. It is a plain for loop making one OpenAI-compatible chat-completions request per item. Run it against OpenAI or a local Ollama/LM Studio server; stop and resume without paying twice.

Markdown is the database

my-brain/
├── raw/<source>/<YYYY-MM>/<id>.md   immutable imported history
├── wiki/<slug>.md                   linked, editable knowledge pages
├── synapse.db                       disposable FTS5 + graph index
└── synapse.toml                     model and owner settings

Delete synapse.db and synapse reindex --vault ./my-brain recreates it. The durable data is ordinary Markdown that works with git, Obsidian, grep, and any editor.

How it works

1. An adapter streams each source into a tiny Item shape with stable IDs and timestamps.
2. Ingest writes immutable raw Markdown and indexes it with SQLite FTS5—no model call.
3. Build compresses one item and asks any OpenAI-compatible model for complete wiki pages.
4. [[wikilinks]] become edges; a recursive SQLite CTE handles multi-hop traversal.
5. The one-file dashboard, CLI, Python API, REST API, and MCP server all use the same vault.

Model providers

Synapse uses one standard-library HTTP POST to /chat/completions; there is no provider SDK.

Set SYNAPSE_BASE_URL, SYNAPSE_MODEL, and (when required) SYNAPSE_API_KEY. See configuration and costs.

Agent access

The MCP server exposes search, read_page, list_pages, neighbors, and read_source. It is a small stdlib JSON-RPC loop over STDIO, so there is no daemon and no MCP SDK dependency. See MCP setup.

Python works too:

from synapse import Vault

matches = Vault("./my-brain").search("launch decision")

Not built, on purpose

Imported text is untrusted data. Synapse never executes it, and agents are instructed never to follow instructions found inside pages. Raw sources remain available for provenance.

Learn and contribute

• Add an adapter—the highest-impact contribution is about 30 lines plus one tiny synthetic fixture.
• Read how the SQLite graph works.
• See CONTRIBUTING.md for the test and pull-request workflow.

Synapse began as the winner of the LangGraph hackathon in London. This is the local-first rewrite that deleted SurrealDB, FastAPI, React, LangGraph, and embeddings so people can actually run it.