Structural Code Parsing
A Tree-sitter turns your codebase into functions, classes, modules and their relationships. Not regex, not string matching — an actual AST.
Bridging the gap between memory
and code structure.
Watches your coding sessions. Reads your code structure. Builds a knowledge graph.
Memory that compounds in a
Knowledge Graph
Everything your coding agent learns, tagged and connected. Decisions link to patterns, patterns link to code — it's the full story of your codebase.
Memory Tags
Decisions, patterns, conventions, architecture, discoveries, incidents and more. Each memory is tagged with a semantic type so your coding agent knows what kind of knowledge it's looking at - not just a generic string.
Relationships
Your coding agent knows the auth refactor contradicts the session management decision. How? Because the memories are linked, not just stored. Track how decisions evolved, trace why a pattern was adopted or surface when two memories conflict.
Semantic Search
Vector similarity via pgvector. Searching for "auth middleware" finds "token validation layer" because, well, that makes sense - approximate nearest-neighbor retrieval returns results in milliseconds.
Observations and Insights
Neuroloom observes patterns during sessions and synthesizes insights from accumulated evidence. Memory accumulates even when you don't explicitly store anything - repeated behavior across sessions becomes a named pattern.
Workspace Isolation
Every workspace is its own world. Your team's knowledge, memories and code graph are completely isolated - workspace A can't see workspace B. Share what you want, keep what you don't. Multi-tenant by design, not by afterthought.
Code-aware with
CodeWeaver
Give your coding agent a mental model of your codebase. And best of all?
Your source code never leaves your computer.
Code Graph Navigation
Trace imports, find callers and understand what depends on what. Ask "what does changing this function affect?" before you change it.
Grounded Memories
Memories link to actual code entities — functions, classes, files and line ranges. A decision about your auth layer connects to your actual code.
Local-First Privacy
CodeWeaver runs locally and only stores structural metadata like names, types, line ranges and relationship edges in Neuroloom.
TypeScript and Python
Tree-sitter grammars for TypeScript and Python ship in the default install. The structural index is queryable from any MCP-compatible agent.
Watch. Learn. Remember.
A raw observation becomes a typed memory, grounded in your codebase and connected to what it caused.
Neuroloom captures every tool use, asynchronously extracts a structured memory grounded in your code, and connects it to related memories in your knowledge graph through typed relationships.
Integration
Built for Claude Code. MCP-compatible with Cursor, Windsurf, Augment Code and other agents. Programmatic access via SDK or REST API for custom workflows.
MCP-Native
Install the Claude Code plugin and Neuroloom starts working immediately - observations, context injection, and a knowledge graph out of the box. MCP-compatible with Cursor, Windsurf, Augment Code and other agents.
Python and TypeScript SDKs
Programmatic access for custom agent integrations. The same typed memory model and graph API, available without the MCP layer when you need direct control.
REST API
Every operation is available over HTTP. Bring your own client, build custom tooling or wire Neuroloom into existing agent pipelines. It's your knowledge graph, so have it your way.
Context fades. Memory doesn't.
Start free. Knowledge graph and CodeWeaver included at every tier. No credit card required.