Your codebase,
indexed once.
Queried by any agent, instantly.

Seam is a local-first CLI and MCP server that gives coding agents semantic access to your repository. No more re-reading the entire codebase on every task.

InstallmacOS / Linux
$ curl -fsSL https://seam.adityamer.dev/install.sh | bash
Get StartedView on GitHub
01

How it works

01

Index

Run seam init . Seam walks your repo, chunks files with tree-sitter, computes embeddings, and stores everything in a local vector database.

02

Search

Query with natural language. Hybrid vector + keyword ranking surfaces the most relevant code across your entire codebase in milliseconds.

03

Context

seam context generates formatted code blocks your agent can paste directly. XML, markdown, or JSON. Ready for Claude, Codex, Cursor.

02

Built for agents

Local-first

Your code never leaves your machine

Offline embeddings, local vector store, zero external dependencies. Privacy by design, not by policy. No API keys, no rate limits, no network required.

SQLite backend, deterministic embeddings, automatic file watching. Works the moment you install. No yaml to write, no daemons to manage.

Zero-config

Sensible defaults

Incremental

Smart indexing

File hashing and tree-sitter chunking. Only re-index what changed. Merkle tree tracks state. Watch mode keeps it fresh automatically.

FastMCP server with search_code, list_files, get_chunk tools. Works with Claude, Codex, Cursor, and any MCP client out of the box.

MCP ready

FastMCP server

Portable

Export / Import

Move your index between machines. Share with teammates. No re-indexing. Archive and restore with a single command.

03

Backends & Providers

Pick what works for your stack. Default is local SQLite + deterministic embeddings for zero-config, offline operation.

Default

SQLite

Local vector store with no dependencies. Ships with Seam. Zero setup.

seam config set backend sqlite
Local

LanceDB

Disk-based vector DB for larger codebases. Efficient columnar storage.

seam config set backend lancedb
Remote

Qdrant

Remote vector backend with metadata-only payloads. Source stays local.

seam config set backend qdrant
Default

Local

Deterministic offline embeddings. No network, no API keys, no quotas.

Cloud

OpenAI

OpenAI-compatible API. text-embedding-3-small or any compatible model.

Local AI

Ollama

Self-hosted embedding models. nomic-embed-text or any Ollama model.

04

Install

One command. Zero configuration. Works offline.

Quick install
$ curl -fsSL https://seam.adityamer.dev/install.sh | bash
uv
uv tool install seam-index
pipx
pipx install seam-index
Index and search
# Index your repo
$ seam init .

# Search instantly
$ seam search "JWT validation"

# Generate context for agents
$ seam context "database pooling"
05

Why Seam?

Without Seam
  • Agent re-reads thousands of files on every task
  • Context window fills with irrelevant code
  • Slow responses, repeated questions
  • Cannot work offline or with rate limits
With Seam
  • Semantic search finds relevant code instantly
  • Context stays focused and precise
  • Fast, accurate responses every time
  • Works completely offline, no API calls

Stop feeding your agent the entire repo

Index once. Query forever. Give your AI coding agent the context it actually needs, without the noise.

Get StartedView on GitHub