sovseal Memory

by sovseal

Not rated
GitHub

About

Local-first, zero-knowledge semantic memory for AI agents with on-device vector search (LanceDB + ONNX) and client-side AES-256-GCM encrypted sync.

Details

Author
sovseal
Categories
AI, Other, Knowledge Base, Search

Usage with VS Code (Copilot / Cline / Roo)

Add to your User Settings (JSON) or.vscode/mcp.json:

{ "servers": { "sovseal-memory": { "command": "npx", "args": ["-y", "@sovseal/mcp-server"] } } }
{ "mcpServers": { "sovseal-memory": { "command": "npx", "args": ["-y", "@sovseal/mcp-server"] } } }

Detect your IDE, configure global connection settings, and write system instructions automatically:

npx -y @sovseal/mcp-server onboard --write --register

Supported: Cursor, Claude Desktop/Code, Windsurf, VS Code (Copilot/Cline/Roo), Zed, Google Antigravity, and OpenCode.

For always-on autonomous agents, run as a long-lived HTTP/SSE server:

SOVSEAL_TRANSPORT=sse SOVSEAL_PORT=4040 npx -y @sovseal/mcp-server

A hosted HTTP/SSE endpoint is available for web-based MCP clients and marketplace validation:

https://sovseal-mcp-server.barrackbobby1.workers.dev/mcp

- AES-256-GCMclient-side encryption with a 96-bit random IV per snapshot
- 256-bit key lives in~/.sovseal/config.json(mode0600) —lose this file, lose every snapshot
- Server only ever sees ciphertext + SHA-256-derived paths; it cannot read your context
- Verified Semantic Recall (VSR)— every load re-derivessha256(canonicalize(payload))and fails closed on mismatch
- Packet-Capture Guarantee— run Wireshark or tcpdump against the server; if you find a single byte of unencrypted context on the wire, the software is free forever

All operations are0 RTT— network is never on the read path.

git clone https://github.com/sovseal/mcp-server.git cd mcp-server

- In another terminal, start the MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

- npm run build: Build the TypeScript project
- npm run dev: Watch for changes and rebuild
- npm run typecheck: Type-check without emitting
- npm run test: Run test suite (Vitest)
- npm run test:watch: Watch mode testing
- npm run bench: Run performance benchmarks

- Website:sovseal.com
- Documentation:
docs.sovseal.com
- Trust Center:
trust.sovseal.com
- Chrome Extension:
Chrome Web Store
- Full Monorepo:
github.com/sovseal/core

Local-first long-term memory for coding agents — in-process embeddings (MLX/CPU), hybrid vector+BM25 search, markdown as source of truth. No cloud, no keys.

Embeddings, vector search, document storage, and full-text search with the open-source AI application database

Semantic search through Dickens' classic tale. Find passages by meaning, theme, or concept - not just keywords.

An MCP server providing semantic search capabilities for APLCart data.

MCP server for Christian scholarship and research — scripture, Greek/Hebrew word data, cross-references, patristic texts, and semantic search,

Local code analysis MCP server with 25+ tools: semantic search, call graph tracing, dependency analysis, and symbol navigation. Built with Tree-sitter and CozoDB. Supports Go, Python, JS, TS.

A local-first code indexer that enhances LLMs with deep code understanding. It integrates with AI assistants via the Model Context Protocol (MCP) and supports AI-powered semantic search.

A server for managing structured project context using SQLite, with support for vector embeddings for semantic search and Retrieval Augmented Generation (RAG).

Access and search EPUB ebook collections using semantic vector search.

Search 286 episodes of product management wisdom from Lenny Rachitsky. Semantic search across 300+ hours of transcripts.

An MCP server that gives Claude, Cursor, and every MCP clientone shared memory that never leaves your machine. On-device vector search via LanceDB + Transformers.js (384-dim embeddings), AES-256-GCM client-side encryption, and write-behind ciphertext sync.0 RTT reads.

Embeds and persists a context fact inside the local on-device memory node.

- content(string, required): A third-person factual statement to store (max 65,536 chars)

- Embeds content on-device (intfloat/multilingual-e5-small, 384-dim, ONNX)
- Writes to local LanceDB — returns immediately
- Ciphertext sync runswrite-behind; nothing blocks the caller
- Automatically de-duplicates and reinforces existing entries
- High-risk PII (SSNs, credit cards, API keys) is automatically redacted before storage

Semantic search over stored memory context. Returns top-K relevant memories by L2 distance.

- query(string, required): Semantic query string to search past memories
- topK(number, optional): Maximum number of memories to return (1–20, default: 5)

- Embeds query on-device (LRU-cached pipeline) → vector search local LanceDB
- 0 RTT— network is never on the read path
- Returns[score=NUMBER id=ID] textfor each match — smaller score = closer semantic match
- Returnsno_matcheswhen the store has no relevant entries

Briefing Context (sovseal://context/briefing)

A summarized, reinforcement-aware briefing of procedural, semantic, and recurring memories. Recommended for bootstrapping new conversations with stored user context.

Recent Context (sovseal://context/recent) —Deprecated

Raw list of the most recently stored context facts. Usesovseal://context/briefinginstead.

System prompt helper that bootstraps a conversation by reading fromsovseal://context/recentbefore the first turn.

sovseal runs 100% on-device. There is no external API key, no cloud dependency, and no account required for local memory operations.

The server supports the following environment variables:

- SOVSEAL_TRANSPORT: Transport mode ("stdio"or"sse", default:"stdio")
- SOVSEAL_PORT: SSE server port (default:4040)

Add this to yourclaude_desktop_config.json:

{ "mcpServers": { "sovseal-memory": { "command": "npx", "args": ["-y", "@sovseal/mcp-server"] } } }

Add to your Cursor MCP settings (~/.cursor/mcp.json):

{ "mcpServers": { "sovseal-memory": { "command": "npx", "args": ["-y", "@sovseal/mcp-server"] } } }

Usage with VS Code (Copilot / Cline / Roo)

Add to your User Settings (JSON) or.vscode/mcp.json:

{ "servers": { "sovseal-memory": { "command": "npx", "args": ["-y", "@sovseal/mcp-server"] } } }
{ "mcpServers": { "sovseal-memory": { "command": "npx", "args": ["-y", "@sovseal/mcp-server"] } } }

Detect your IDE, configure global connection settings, and write system instructions automatically:

npx -y @sovseal/mcp-server onboard --write --register

Supported: Cursor, Claude Desktop/Code, Windsurf, VS Code (Copilot/Cline/Roo), Zed, Google Antigravity, and OpenCode.

For always-on autonomous agents, run as a long-lived HTTP/SSE server:

SOVSEAL_TRANSPORT=sse SOVSEAL_PORT=4040 npx -y @sovseal/mcp-server

A hosted HTTP/SSE endpoint is available for web-based MCP clients and marketplace validation:

https://sovseal-mcp-server.barrackbobby1.workers.dev/mcp

- AES-256-GCMclient-side encryption with a 96-bit random IV per snapshot
- 256-bit key lives in~/.sovseal/config.json(mode0600) —lose this file, lose every snapshot
- Server only ever sees ciphertext + SHA-256-derived paths; it cannot read your context
- Verified Semantic Recall (VSR)— every load re-derivessha256(canonicalize(payload))and fails closed on mismatch
- Packet-Capture Guarantee— run Wireshark or tcpdump against the server; if you find a single byte of unencrypted context on the wire, the software is free forever

All operations are0 RTT— network is never on the read path.

git clone https://github.com/sovseal/mcp-server.git cd mcp-server

- In another terminal, start the MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

- npm run build: Build the TypeScript project
- npm run dev: Watch for changes and rebuild
- npm run typecheck: Type-check without emitting
- npm run test: Run test suite (Vitest)
- npm run test:watch: Watch mode testing
- npm run bench: Run performance benchmarks

- Website:sovseal.com
- Documentation:
docs.sovseal.com
- Trust Center:
trust.sovseal.com
- Chrome Extension:
Chrome Web Store
- Full Monorepo:
github.com/sovseal/core

Local-first long-term memory for coding agents — in-process embeddings (MLX/CPU), hybrid vector+BM25 search, markdown as source of truth. No cloud, no keys.

Embeddings, vector search, document storage, and full-text search with the open-source AI application database

Semantic search through Dickens' classic tale. Find passages by meaning, theme, or concept - not just keywords.

An MCP server providing semantic search capabilities for APLCart data.

MCP server for Christian scholarship and research — scripture, Greek/Hebrew word data, cross-references, patristic texts, and semantic search,

Local code analysis MCP server with 25+ tools: semantic search, call graph tracing, dependency analysis, and symbol navigation. Built with Tree-sitter and CozoDB. Supports Go, Python, JS, TS.

A local-first code indexer that enhances LLMs with deep code understanding. It integrates with AI assistants via the Model Context Protocol (MCP) and supports AI-powered semantic search.

A server for managing structured project context using SQLite, with support for vector embeddings for semantic search and Retrieval Augmented Generation (RAG).

Access and search EPUB ebook collections using semantic vector search.

Search 286 episodes of product management wisdom from Lenny Rachitsky. Semantic search across 300+ hours of transcripts.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.