Resources
Resources
Writing on memory, agents, and a preprint on where small readers fail. Setup guides follow when delivery surfaces exist.
Blog
The small reader missed facts that were already in the prompt
I wrote a preprint on this. On one development split, most of the misses happened with the evidence already loaded. I am not claiming a win over Mem0.
2026-10-11 · 2 min
How I actually built the memory
Sources come in. Notes keep the date and who said it. A newer decision marks the older one. An MCP client receives the current context.
2026-10-11 · 2 min
The agent was useful the second time, not the first
The first session is a briefing. The second session is where memory either shows up or you paste the same thread again.
2026-10-11 · 1 min
The old decision was still in the notes
On 1 October we parked SSO. On 2 October we shipped it with the Team plan. Both notes exist. Only one is current.
2026-10-11 · 1 min
I did not want a store I have to query
A store waits for a query. I wanted the agent to receive the current context when it starts work.
2026-10-11 · 1 min
Mem0, Zep, Letta, and what I am not claiming
They are memory systems you query from your own agent. I give the current context to the agent. There is no head-to-head score on this page.
2026-10-11 · 2 min
I use more than one AI in a day
The memory should not live inside one chat product. I connect the tools once and point each MCP client at the same server.
2026-08-12 · 1 min
I would rather the agent say it does not know
A fluent sentence with no note behind it is the bug I am trying not to ship.
2026-08-10 · 1 min
MCP is the socket, not the memory
MCP is how a client calls a tool. Archilas is the tool that hands back the current context.
2026-08-08 · 1 min
The context died when I closed the tab
The model did not forget. The session ended. The next tool opened with an empty prompt.
2026-08-06 · 1 min
Search found the paragraph. It did not know which decision won
RAG is how I pull a passage. It is not how I know the October decision replaced the September one.
2026-08-04 · 1 min
Research
Evidence in Context Is Not Enough
Preprint by [OPERATOR NAME]. Why a small reader fails at long-term conversational memory even when the evidence is already in the prompt. Not peer reviewed.
Guides
Slack, GitHub, Gmail, Notion, Linear, Google Calendar, Google Drive, and AI chats are connected. Compatible with any AI that supports MCP. Cursor, Claude Code, ChatGPT, and Codex are examples.
Pricing
Free is 100 questions a month, one integration, and all AI chat context. Every paid plan includes all integrations.
See pricing