Instinct compression pipeline — knowledge distillation and adapter export

📜 Napkin integration for pi — vault context, knowledge tools, and automatic distillation with git-worktree concurrency safety

Stateful agent tools for OpenCode. Learns who you are, remembers what you're working on, schedules tasks, maintains itself.

A Software Development Kit (SDK) for Zero-Knowledge Transactions

MCP server for enabling memory for Claude through a knowledge graph

Using TypeScript as a knowledge base

Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing

Ship compositional knowledge for AI coding agents alongside your npm packages

Agent-friendly local knowledge CLI with JSON output, pagination, and safe destructive actions

BuilderForce Agent Memory — runtime layer. SSM execution, Transformer orchestration, online distillation, hybrid RAG retrieval, and persistent agent memory for BuilderForce.ai agents.

TOGA Technology Team Claude Knowledge System — shared AI coding harness with skills, knowledge base CLI, and project installer for Claude Code.

HorizonDB-backed enhanced facts and graph providers for PilotSwarm.

Local-first, agent-friendly Markdown knowledge base with a cross-platform CLI and web editor

Decision-moment skills distilled from «Building Applications with AI Agents» (Albada, рус. пер.) — makes an AI coder apply the book's agent-engineering methodologies. 17 skills over both distillation waves. Machine-distilled (trust_tier 1, routing-gated),

Client for API Gateway handlers, bypassing API Gateway by directly invoking the Lambda

Minimal GraphQL client supporting Node and browsers for scripts or simple apps.

dsh-plugin: quality-first topic memory for dsh — a topic keeps the starting question, conclusion, impact and dependencies, not the process; local-first git-traced OKF bundle, budgeted LLM-free injection

Decision-moment skills distilled from «Высоконагруженные приложения» (M. Kleppmann, DDIA рус.) — makes an AI coder apply the book’s data-systems methodologies. Machine-distilled (trust_tier 0), book-derived (paraphrase, not quotation).

Local-file LLM Wiki plugin for source ingestion, wiki browsing, query, lint, and maintenance workflows. Maintained fork of @paperclipai/plugin-llm-wiki.

Build, search, evaluate, and improve source-backed knowledge bases.