Assistant-scoped memory composition layer over @agent-relay/memory

Project-scoped memory layer for Claude Code, Codex, Hermes, MCP, and dashboards

Portable, project-scoped memory and session handoffs for coding agents. Readable files, MCP recall, and optional user-passphrase encrypted backups.

Noopolis scoped memory runtime and MCP tools for agentic systems.

Host plugin: durable, correctable, scoped memory over an append-only event ledger

Pi extension for scoped memory cues, historical source search, and full-fact recall.

Ethos — TypeScript AI agent framework where personality is architecture. Curated toolsets, first-person identities, scoped memory.

Lossless, project-scoped memory for AI coding tools. Durable context across sessions with MCP tools, FTS5 search, cloud sync, trace optimization, Claude/Codex/OpenCode/Gemini wrappers, skill packs, and automatic hooks.

MCP server for project-scoped memory stored in .github/memories

AgentMemory is a private, device-scoped memory service for AI coding agents. It keeps durable memories, lessons, sessions, and search available across a workstation while running the backend at the Cloudflare edge.

Governed agent-harness core: scoped memory, token ledger, eval-gated learning, flows, MCP.

Agent-curated long-horizon memory (ctx.memory) for DeepSeek Harness: durable project-scoped memory banks with a provider registry and a shipped local backend — a standalone plugin with no upstream harness changes required.

The engine behind Asterism: agent identities, scoped memory, secrets, trust levels, and the event log. You probably want @qmilab/asterism.

Cerebro persistent memory plugin for OpenCode — auto-recall, auto-capture, 9 memory tools with clustering, project-scoped memory isolation

Task orchestration for the Exellix stack: runTask() with local handlers or LLM-backed execution, task-scoped memory/context enrichment, and executor dispatch via @exellix/ai-skills. ERC-compliant.

Branch-scoped memory for Claude Code — isolate conversation context per git branch

MCP server that gives AI agents persistent, project-scoped memory backed by MongoDB

Babel plugin to ensure function declarations at the block level are block scoped

ReMEM v2 core: scoped memory planning, recall, extraction, graph expansion, and bounded context assembly for agents

db0 memory plugin for OpenClaw. Persistent scoped memory, automatic fact extraction, sub-agent support, compaction safety.