Symbolic computing and numeric evaluations for JavaScript and Node.js
Canvas for Node.js with skia backend
Project governance CLI — tasks, epics, ADRs, wiki indexing
Match balanced character pairs, like "{" and "}"
A light-weight module that brings Fetch API to node.js
CLI to initialize and manage Cortex Context (Knowledge Graph) in any VS Code workspace
OpenClaw plugin for Cortex memory — Auto-Recall, Auto-Capture, and agent memory tools
Local, repo-scoped context platform for coding assistants. Semantic search, graph relationships, and architectural rule context.
All four BLAKE2 variants (blake2b, blake2bp, blake2s, blake2sp) for Node.js, with stream support
## Introduction
Sync Claude Code sessions between machines with automatic path remapping and skill conversion
Send samples to prometheus via remote_write from NodeJS
Match balanced character pairs, like "{" and "}"
Local-first memory for your AI brain — a nervous system that turns engrams into curated, persistent memories in a folder you control. Bundles `think serve` for piping external events (GitHub, Linear, …) into memory.
Unified documentation standards and tooling for Cortex repositories with LLM optimization
Traverse JSON Schema passing each schema object to callback
Cortex service adapters for Pacta — LLM provider, audit middleware, RFC-8693 token-exchange middleware
Autonomous agent system for long-running projects — mission-driven, multi-agent pipelines, self-evolving skills.
[](https://www.npmjs.com/package/@aws-sdk/s3-presigned-post) [](https://www.npmjs.com/package/@
A light-weight module that brings window.fetch to node.js
Local project rehydration, file discovery, and session-history MCP server for AI agents (Claude Code, Codex)
Implementation of window.fetch which can use http2 seamlessly
Code intelligence MCP server. Indexes your repository into a queryable call graph for AI coding agents.
Core helpers for creating a Cortex plugin
Intelligent conversation memory system for AI assistants — persistent knowledge storage, semantic search, knowledge graph, MCP + gRPC transports. Facade crate re-exporting the post-cortex workspace stack.
Storage backends for post-cortex — lock-free RocksDB (default) and optional SurrealDB. Implements the Storage trait against the post-cortex domain types.
Model Context Protocol (MCP) tool definitions for post-cortex. Pure library — embed in rmcp, custom MCP servers, or anywhere else; no rmcp / axum / tonic transport dependencies.
Protobuf + tonic-generated wire types for post-cortex. Domain-neutral; safe to depend on from gRPC clients without pulling the full server stack.
HTTP / gRPC / SSE / stdio daemon for post-cortex. Hosts the rmcp Model Context Protocol surface, the tonic gRPC API, and ships the `pcx` CLI binary.
Conversation memory orchestrator for post-cortex. Ties storage + embeddings + graph + session + summary into a single lock-free memory hierarchy with async pipelines and a canonical PostCortexService API.
Core domain library for post-cortex: lock-free conversation memory, semantic search, knowledge graph, and storage backends. Transport-agnostic — no axum/tonic/rmcp.
Embedding engines (Model2Vec static + BERT via Candle + static-hash fallback) and HNSW vector database for post-cortex. Self-contained ML stack — depend on this crate when you need vector search without the full post-cortex orchestrator.