Get the weekly radar
One short email with the freshest products, every week.
Scritty captures every AI CLI agent's chats into one searchable memory, accessible anywhere.
Grounded in available product and source data
Claude Code in the morning, Codex in the afternoon — that's two separate, disconnected conversation histories for most developers. Scritty is unified memory across every AI CLI agent, sitting at the terminal boundary where every CLI agent has to cross and capturing what happens regardless of which one is running.
Detection is agent-agnostic by design: Scritty identifies which AI agent is active through process analysis rather than by parsing prompt text, then records both sides of the exchange, tagged by provider and session. That builds into one searchable corpus spanning Claude Code, Codex, Copilot CLI, Antigravity, Grok, Aider, and Ollama, queried through hybrid search — vector plus keyword search fused together — with offline ONNX embeddings handling code and prose separately.
That memory isn't locked to the terminal it was captured in either. A terminal panel offers inline search on demand, an MCP server exposes it to local or remote agents, a CLI provides direct command access, browser sync mirrors the same session live across desktop and browser, and a mobile PWA pairs by QR code and keeps working offline with auto-reconnection. On the control side, standing instructions defined once in a prompt.toml file apply across every connected agent, and Scritty reads vendor-native rule files like CLAUDE.md directly rather than requiring a separate configuration format.
Running natively on macOS, Windows, and Linux, Scritty can even become the system default terminal on Linux and Windows, and it's tmux-aware — separate panes stay separate in the captured record rather than bleeding into one conversation. Pricing runs on exchange volume rather than per-seat: an entry no-cost option gives 25,000 exchange-pairs with no account needed, a one-time Personal purchase covers unlimited local capture for solo use, and team tiers scale up through a metered federated-pairs allowance for shared, central memory across an organization — worth noting that local capture stays unlimited on every paid tier regardless of team size.
No — capture is agent-agnostic, detecting which agent is running through process analysis, and the resulting corpus spans Claude Code, Codex, Copilot CLI, Antigravity, Grok, Aider, and Ollama in one searchable place.
A QR code scan through the mobile PWA is the whole setup, and it keeps working offline with automatic reconnection once a connection comes back.
Not directly — cost tracks how much gets exchanged through the shared plane, not how many people are logged in, so a small, high-usage team could cost more than a larger, lighter-usage one.
No — the site states a Personal-tier license never contacts Scritty's servers, with no heartbeat, expiry, or kill switch built into an owned copy.
No — vendor-native rule files get read directly as they already exist, so an existing setup doesn't need to be duplicated into a Scritty-specific format.
These 1 comments were collected from the discovery source. ProductVisit does not host replies in Release A.
I built scritty because I got tired of agents making me repeat myself. Deep into a problem on Claude, I'd hit the usage limit mid thought or debugging, so then I would go over to Copilot which is now a new empty session, so I'd bring it up to speed by pasting context back in. Hit that wall and then I do the same thing on Codex. Run that one dry and I'm off to Antigravity. Burn that out and don't want to wait for limit refreshes so switch to running local Ollama and repeat. Same project the whole way, and every switch turns into the same tedious, token-wasting chore: copy+pasting old conversation, dropping in screenshots, jamming as much as I can into the prompt and hoping for the best. So I built a terminal they all run inside. It sits where every one of them already is, captures the conversation as it happens, and turns it into one searchable memory that carries across every switch. You run any AI CLI inside scritty. It detects what agent is running from the process itself, tags every exchange with the provider, and indexes it locally into an embedded vector store (swappable if you already run qdrant, pgvector, chroma, or weaviate). Search is hybrid and fully offline. Then it exposes that knowledge base over an MCP server and a CLI, so your agents can query their own and each other's past turns, and you can query it as you work. Two things I use every day: - prompt.toml: Because I own the terminal, I can write my rules once and scritty injects them into every message before it reaches whichever agent is running, plus that vendor's own rule file. Markdown files with rules are great, but their relevance is prone to decay, whereas this is in the agent's face every turn (or toggle it off when you don't need/want it). - Phone sync: same terminal session is live on my phone as a PWA. I start something at my desk, walk away, and pick it up on my phone, both ends in sync. My favorite part. It is local-first and paid. Personal is $19.99/mo and runs entirely on your machine with no cloud account; there is a free 14-day pilot and no permanent free tier. Your agents already keep memory, but it is locked in each vendor's box and metered when you reach back into it; scritty's lives on your machine and is free to query, offline. One agent gives you a searchable memory of your own work; every agent you add shares the same corpus. It scales to teams as a shared enforcement layer and a federated, access-controlled, auditable knowledge base, with a per-org control plane for members, billing, seats, audit, license, SSO and SAML, which is a part I really care about coming from regulated environments (banking, healthcare, public sector). Sessions are private by default and you opt into what gets shared. And because capture is at the terminal and not inside any vendor, the agent vendor is swappable: Claude this quarter, Codex or Antigravity the next, nothing lost and no data migration, because the knowledge base is yours and agents rotate through it. There's a 3:09 demo on the site. The whole point is I never start cold again: whoever I'm working with (agent or dev team) can pull up everything the last one already figured out. Happy to answer anything. Show more