Text memory plugin for DeepSeek Harness that saves source-linked preferences and project decisions, reviews writes before they become effective, and keeps historical values separate from current rules. Public beta, MIT license.
Pricing as listed on the vendor site on Nov 12, 2026: free tier Free: MIT-licensed plugin you install in DeepSeek Harness. Public beta; the README says saving or recall may fail.; paid from Free (MIT license).
Is this your tool?
Get SoloPup Memory featured in Memory & Context for $99/month. You get a labeled featured badge and a top spot in the category. Or claim the listing for free to request edits.
Secure checkout via Stripe. Cancel anytime.
Head to head
Memory & Context
Memory layer that lets agents learn from past interactions.
Context layer that unifies business data, documents, and chats for agents.
Platform for building stateful agents that learn from experience.
Open-source agent memory platform built on graph and vector stores.
Memory and continual learning engine for agents.
Versioned markdown context vault for agents, read through a CLI or an MCP server.
MemorySync is a memory API for AI applications: your agent writes what it learns about each user, and MemorySync returns the relevant parts later, ranked by meaning and scoped to that user.
Shared workspace your AI agents work from: files with version history, tables, tasks any agent can pick up, and pinned decisions every agent reads when it loads the workspace. Agents connect from Claude, ChatGPT, Codex, Cursor or any MCP app through a hosted MCP server, a CLI or an HTTP API, each with its own revocable key, and every change is logged with the agent that made it.
Company memory for agents: a shared memory of people, customers, decisions and promises, plus connectors to the company's systems, reached through an OpenAI-compatible API, an Anthropic Messages endpoint and an MCP server. Routes across the model keys you already hold and does not resell tokens.