翻訳待ち：Show HN: Knownbase, an MCP server for persistent AI agent memory

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。

Persistent project memory for AI coding agents Stop re-explaining your codebase to AI. Knownbase gives your AI coding agents persistent, searchable project knowledge, so architecture decisions, debugging discoveries, conventions and lessons survive across sessions and tools. See how it works Works with Claude Code, Codex, Cursor, ChatGPT and any MCP-compatible agent. Free plan, no card required. Why we dropped the queue-based importerdecision · payments-api · still current Flaky checkout test = timezone in parseDatedebugging · payments-api · resolved Prod Mongo has no Atlas Search — regex fallback onlyconstraint · payments-api · load-bearing { "mcpServers": { "knownbase": { "url": "https://knownbase.dev/mcp" } } } Survives the sessionKnowledge lives outside the context window, so ending a conversation doesn't end what the project knows. Shared across agentsOne workspace that Claude Code, Codex, Cursor and your teammates' agents all read and write. Retrieved, not reloadedAgents search for the slice they need instead of loading an ever-growing instruction file every time. The problem Your AI is smart. Your project knowledge keeps disappearing. None of these are model failures. They're storage failures: the agent learned something real and had nowhere durable to put it. New session, same explanationsEvery fresh conversation starts by re-describing the architecture, the conventions and the constraints you explained yesterday. Compaction loses the discoveriesThe context gets compacted mid-task and the hard-won finding from two hours ago is summarized down to nothing. What compaction actually drops → Agents repeat solved problemsThe same bug gets re-diagnosed from scratch, and the same rejected approach gets proposed again next month. Why this keeps happening → Claude and Codex don't share anythingWhatever one agent figured out is invisible to the other, so switching tools means rebuilding context by hand. Share context between them → Decisions vanish into old chatsThe reasoning behind a schema, a library choice or a rejected design is buried in a conversation nobody can search. The instruction file keeps growingCLAUDE.md creeps toward a thousand lines because it's the only place knowledge can go. Instructions vs memory → The outcome Project knowledge that survives the conversation. An agent writes what it learned. Every later agent — yours, a different tool, a teammate's — can search for it. Agent at workMakes a decision, corners a bug, hits a constraint. → KnownbaseStores it as a versioned, searchable, project-scoped note. → Searchable project memoryOrganised by project, tag and status. Linkable and revisioned. → The next agentRetrieves exactly the relevant slice and continues. What agents store Git remembers what changed. Knownbase remembers why. Version control is a perfect record of every diff and a terrible record of the reasoning behind it. The reasoning is what an agent needs and what git was never designed to hold. Architecture decisions Why this library, this schema, this trade-off — captured once so no agent relitigates it three months later. Debugging discoveries The investigation that finally explained a flaky test, so the cause survives past the session that found it. Rejected approaches What you already tried and why it failed. The single highest-value thing to store, and the one nothing else records. Operational constraints The deployment landmines, rate limits and environment quirks that only reveal themselves in production. Project conventions How this codebase does errors, naming, tests and migrations — the local dialect an agent has to match. Session handoffs What's done, what's in progress, and the one next step, ready for the next agent. How to write one → Differentiation Instructions aren't the same as memory. CLAUDE.md and AGENTS.md are good at what they do. They're just solving a different problem, and using one for the other is why instruction files end up unmaintainable. CLAUDE.md / AGENTS.mdKnownbase What it holdsStanding instructions: how to behave in this repo.Accumulated knowledge: what has been learned about this project. How it's loadedEntirely, into every single session.Searched on demand; only the relevant slice enters the context. How it scalesStays useful while it stays short. Costs context on every turn as it grows.Grows without bound. Retrieval cost doesn't grow with the store. Who writes itYou, by hand, in a text editor.The agent, as it works, over MCP. HistoryWhatever git shows for the file.Per-note revisions, with links between related notes. ReachOne repo, one tool's conventions.One workspace, every MCP client and teammate. Keep the instruction file for rules. Move the growing pile of decisions and discoveries into project memory. The full comparison, with a worked example → Multi-agent Switch agents, not context. Project memory that belongs to the project rather than to whichever tool happened to be open when the knowledge was created. Claude CodeFinds the real cause of a production incident and writes it down. → One shared workspaceProject-scoped, searchable, versioned. Reachable over MCP from anywhere. → Codex · Cursor · ChatGPTRetrieve that finding on a later task without you re-typing a word of it. Claude Code One command to connect, OAuth sign-in, no key to paste. Set up Claude Code → Codex Same endpoint, same workspace, same notes. Set up Codex → Cursor Add one entry to mcp.json and Cursor gains project memory. Set up Cursor → How it works Three steps to project knowledge that outlives the session. No SDK, no vector database to run, no repo changes. One MCP endpoint your agent already knows how to talk to. 1Connect over MCP Point Claude Code, Codex, Cursor or ChatGPT at https://knownbase.dev/mcp and sign in. Setup instructions → 2Store as you go The agent calls upsert_note when it decides something, discovers something or hits a constraint worth keeping. 3Recall on demand Any later agent calls search_notes, pulls only the relevant notes into context, and continues from there. Affordable plans Start free, upgrade when your agents need more memory. Every paid plan starts with a 7-day free trial. No charge until it ends, cancel anytime. FAQ The questions developers actually ask first Why does my AI coding agent forget my project between sessions? Because a context window is working memory, not storage. Everything an agent learned during a session — why you rejected an approach, what actually caused a bug, which deployment constraint bit you — lives in that conversation and disappears when the session ends or the context is compacted. Knownbase keeps that knowledge outside the context window, in a store the next session can search. Isn't that what CLAUDE.md or AGENTS.md is for? Those files are instructions: a small, hand-maintained set of rules loaded into every session. Knownbase is accumulated knowledge: hundreds of decisions, debugging trails and constraints that an agent retrieves only the relevant slice of. Instruction files stay small and get loaded every time; project memory grows without end and gets searched on demand. Most teams want both. Which agents and tools work with Knownbase? Anything that speaks the Model Context Protocol: Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, and local agents. Point the client at https://knownbase.dev/mcp and sign in with OAuth, or paste an API key. The agent then gets tools such as search_notes, get_note and upsert_note. Can two different agents share the same project memory? Yes — that is the point. A workspace is a shared store, so a discovery Claude Code writes today is retrievable by Codex, Cursor or a teammate's agent tomorrow. You switch agents without rebuilding context. Is my project data isolated and secure? Every note is scoped to your workspace and never shared across tenants. Sessions and API keys are stored hashed, passwords use PBKDF2, and keys can be made read-only or restricted to a single project. Your content is never used to train models. You can export or delete everything at any time. Read the full security and data-ownership page. Can I start for free? Yes. The Free plan includes 3 projects, 300 notes, and 2 MCP keys, with no card required. Paid plans each start with a 7-day free trial. From the blog How persistent agent memory actually works. Claude Code Claude Code keeps forgetting your project? Why it happens, what CLAUDE.md and auto-memory each cover, and how to add persistent memory. Context Context compaction: what gets lost What a compaction pass actually drops, and how to make the important findings survive it. MCP MCP memory servers explained What an MCP memory server is, the kinds that exist, and which one fits which problem. Read the blog → Featured on Find Knownbase across the startup community.