Project memory layer for coding harnesses
Cross-harness memory for agents.
Typed memory kernel models for meego-harness
Deep Agents - a library for building controllable AI agents with LangGraph
Zep-backed Memory MCP implementing the SOA-Harness §8.1 6-tool protocol. Maps Zep's Document Collection API to the canonical hit shape; ≤300-LOC shim per Gate 4 constraint.
Stable application runtime and operator control plane for agent workspaces.
mem0-backed Memory MCP implementing the SOA-Harness §8.1 6-tool protocol. Qdrant vector store + OpenAI or local Ollama LLM/embedder.
SQLite-backed Memory MCP implementing the SOA-Harness §8.1 6-tool protocol. Zero external services; ships the spec-canonical 'hits' wire shape.


Memory bridge for Claude Code and Codex — local-first, zero-cost coding memory runtime




Bounded iterative assistant-turn runtime for Agent Assistant SDK
Core platform abstractions for React Native Harness

Metro bundler for React Native Harness
Apple platform for React Native Harness


Android platform for React Native Harness
Declarative control plane for agent harnesses — one YAML for grounding, tools, memory, and hooks.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.