Knowledge & Memory

An opinionated Agent Development Kit for building custom AI agents with bring-your-own infrastructure and opt-in batteries.

Vault-first persistent memory for AI coding agents, with an optional profile-aware governance runtime: OFF, FLOW, GUIDE, GOVERN, or ASSURE. Local-first and agent-agnostic (Claude Code, Codex, Cursor…).

Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.

Code intelligence graph — MCP server + AI agent skills + visualization UI

Governed Call Telemetry release planning MCP server and CLI

Edda — the company data layer for AI agents.

MCP server giving Claude a long-term memory in a GitHub repo you own

Standalone Agent Client Protocol (ACP) server for DeepSeek Harness with real-time streaming, thought visibility, tool lifecycle updates, and session recovery.

4,352 pre-production checks: security, performance, scale, integrations, post-launch.

Deterministic, persistent graph server for tracking workflow state, decisions, and blockers.

CogMemory MCP Server — Unified context subsystems for AI coding agents

Local visual UI cache for AI agents using perceptual hashing + CLIP to cut vision token use.

Persistent self-improving agent memory with tree-of-thoughts reasoning: MCTS/beam search, PRM step verification, self-consistency voting, s1 budget forcing, REPL program-aided reasoning, reflexion self-correction, failure classification, experience replay

Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.

Memory protocol enforcement plugin for DeepSeek Harness — forces memory_weave before tool calls, auto-ingests session turns, injects memory context into agent steps. Bridges the opencode-memory MCP server with a hard protocol gate.

MCP server for local codebase indexing, semantic search, and code dependency graphs.

Memory layer for AI coding assistants. Indexes git history + code, exposes via MCP.

Associative key-graph memory for LLM agents — recall by association, not vector similarity.

OpenCode plugin — define custom AI agent roles via YAML with per-role prompts, models, skills, and permissions

One section in, one section out — on Markdown/GEML files, bad writes refused.