Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.
io.github.everest-an/awareness-local — Model Context Protocol (MCP) Server
The MCP server provides local-first persistent memory for AI coding agents. Its description highlights performance results of 96.0% R@5 on LongMemEval and notes zero LLM calls, indicating memory retrieval or usage does not require additional model invocations. Data is scoped to the server’s documented capabilities.
🛠️ Key Features
Local-first persistent memory for AI coding agents
Reported 96.0% R@5 on LongMemEval
Zero LLM calls
🚀 Use Cases
Supporting AI coding agents with persistent memory on local systems
Use in evaluation contexts aligned with LongMemEval
⚡ Developer Benefits
No LLM calls needed for the described operation
Demonstrated ranking quality via LongMemEval metric (R@5)
⚠️ Limitations
Only the provided description and metrics are specified; no additional tools, topics, or configuration details are included
Your AI agent forgets everything when the session ends. Awareness fixes that.
Awareness is a memory plugin for AI coding agents — Cursor, Claude Code, Copilot, Cline, OpenCode, and any MCP client. It stores what you decided and what you learned as plain Markdown on your machine, then recalls it in the next session: hybrid keyword + semantic retrieval, 96% R@5 on LongMemEval, zero LLM calls at retrieval. Works offline, no account required.
Install with one command:
bash
npx @awareness.market/setup
It runs a lightweight daemon on your machine, stores memory as Markdown, indexes recall with SQLite FTS5 + embeddings, and keeps your AI workflow fast, explainable, and offline-ready.
bash
npx @awareness.market/setup
That's it. Your AI agent now remembers everything across sessions.
AI coding agents lose context between sessions. Awareness Local provides cross-session memory recall so agents can continue work without re-explaining architecture, past decisions, pending tasks, and implementation constraints.
Persistent memory for AI coding agents
Local-first MCP server with offline support
Hybrid retrieval (keyword + semantic)
Knowledge card extraction for decisions, solutions, and risks
Quick Start
bash
npx @awareness.market/setup
Then open your IDE and start coding. Awareness tools become available for recall, record, and session initialization.
Popular Use Cases
Long-running codebase migrations across many sessions
Team handoffs where AI should remember prior implementation context
Personal coding workflows that need durable preferences and conventions
Multi-agent setups that share decision history and task memory
FAQ
Does Awareness Local work offline?
Yes. Local mode works fully offline with memory stored on your machine.
Where is data stored?
Memory is stored as Markdown in .awareness/, with a local SQLite index for retrieval.
Do I need a cloud account?
No. Cloud sync is optional and can be enabled later.
Which IDEs are supported?
Any MCP-compatible IDE, including Cursor, Claude Code, Copilot, Cline, Windsurf, and others. ChatGPT Desktop: Settings → MCP servers → Add server → Streamable HTTP → http://127.0.0.1:37800/mcp (local daemon only, no auth needed).
Evaluated on LongMemEval — the industry standard benchmark for long-term conversational memory. 500 human-curated questions across 5 core capabilities.
Before: Every session starts from scratch. You re-explain the codebase, re-justify decisions, watch the agent redo work.
After: Your agent says "I remember you were migrating from MySQL to PostgreSQL. Last session you completed the schema changes and had 2 TODOs remaining..."
code
Session 1 Session 2
┌─────────────────────────┐ ┌─────────────────────────┐
│ Agent: "What database?" │ │ Agent: "I remember we │
│ You: "PostgreSQL..." │ │ chose PostgreSQL for │
│ Agent: "What framework?"│ → │ JSON support. You had │
│ You: "FastAPI..." │ │ 2 TODOs left. Let me │
│ (repeat every session) │ │ continue from there." │
└─────────────────────────┘ └─────────────────────────┘
If Awareness Local saves you from re-explaining your codebase to your AI agent, give it a ⭐ — it helps more developers discover the project and pushes it toward GitHub Trending.