97% token reduction for AI coding. Extracts function & class signatures with TF-IDF ranking to feed only the right files to Claude, Cursor, Copilot, Aider, Windsurf, local LLMs & MCP. Zero dependencies, runs offline via npx.
Cited, access-bounded local-memory retrieval for OpenClaw: access boundary, redaction, citations, and opt-in enhanced memory sidecars.
Retrieval latency ladder benchmarks + CI regression gates for @remnic/core
Turn a directory of documents into a portable, queryable knowledge base
SharkCraft structured knowledge model: typed entries, index, search, loaders (TS + markdown), validation.
prom.codes Context — local-first codebase indexing & retrieval as an MCP server.
An opinionated Agent Development Kit for building custom AI agents with bring-your-own infrastructure and opt-in batteries.
Local-first indexing and retrieval engine for AI coding agent repo memory, org memory, GitHub PR history, codebase evidence, regressions, and cross-repo impact.
AI-native dual-graph knowledge representation — build, query, and persist typed knowledge graphs in-process.
Retrieval, context packing, provenance, and prompt-injection guard contracts for Plasius AI RAG.
Developer-facing retrieval SDK over valkey-search: index lifecycle, upsert, vector + filtered query
Pointwise mutual information (PMI) co-change coupling mined from git history — find the files that change together.
AI-ready Laravel 13 skills, rules, agents, deterministic retrieval CLI, and MCP server
Core Markdown vault indexing, retrieval, and search logic for vault-agent.
Model Context Protocol server for Agentic Task System — exposes the task app you already use to any MCP client, backed by hybrid + RRF retrieval. Storage-agnostic over the ATS adapter contract.
Shared libraries and services for platform builders and agents — CLIs, retrieval, evaluation, and infrastructure published to npm.