Project memory for coding agents

Give your AI amemory that lasts.

Human-curated, project-scoped context for the current task — not another generic vector store. Capture what matters, organize by project, and connect agents over MCP.

No credit card required · Works with OpenAI, Anthropic, Gemini

Plays nicely with the models you already use

OpenAIAnthropicGeminiOpen source

The problem

LLMs forget. Context windows fill up. Your app pays the price.

Every prompt is a fresh start. You pad the context with history, hit token limits, watch quality drop, and burn money on tokens the model doesn't need to see.

Bloated prompts

Stuffing chat history into every request wastes tokens and slows responses.

Lost knowledge

Users repeat themselves across sessions. The model never learns who they are.

Fragmented context

Notes, docs, and decisions live in five different tools — none of which the LLM can see.

Features

Project memory — not generic vector infrastructure

Tasks, curated context, and MCP tooling that keep agents aligned with how your team already works.

Human-curated memory

Notes, docs, links, and decisions you choose — not auto-ingested chat sludge.

Current-task focus

Agents load the active task and its scoped context, session after session.

Project namespaces

Organize by project or bucket. No bleed between tenants or workstreams.

MCP-native

Drop-in MCP server for Cursor, Copilot, Claude, ChatGPT, Codex, and HTTP clients.

Private by default

Row-level security, encryption at rest, and full audit trail.

Built for agent loops

Fast reads so getTaskContext and search stay snappy in the coding loop.

How it works

Capture → Organize → Connect MCP

A project-centric workflow built around the current task — curated by humans, consumed by agents.

Capture

Save what the team already decided

Attach notes, docs, links, and decisions to a project or task — human-curated context, not a dump of chat embeddings.

Project · checkout-latency
  • API contract notestext
  • Design review Figmaurl
  • Incident postmortemdoc

+ Add context — you choose what agents may see

Pricing

Start free. Scale when you ship.

Hobby
$0/mo

For prototypes and side projects.

  • 10k memories
  • 1 project
  • Community support
Start free
Pro
$29/mo

For teams shipping AI features.

  • 1M memories
  • Unlimited projects
  • Priority retrieval
  • Email support
Start Pro trial
Enterprise
Custom

For regulated and high-scale workloads.

  • Dedicated infra
  • SSO + audit logs
  • SLA & DPA
  • Solutions engineer
Contact sales

Ready to give your AI a memory?

Spin up your first memory store in under a minute. No credit card, no setup calls.