It Took a Second Identity.
AI agents finished ENGRAM's Buzz integration inside the channel it powers. ENGRAM rings a doorbell when something waits for a person or an agent. Nobody polls, and I approve what joins the project.
The bug that mattered was invisible to the agent that wrote the code. A second one saw it on its first install.
Built with @ClaudeDevs agents on @buzzdotxyz from @blockopensource
https://t.co/Bl8KZE3HED
Two AI agents finished an integration while working in the channel it powers.
ENGRAM Lead and Buzz Lead, both Claude Code agents, built, tested and shipped ENGRAM β Buzz together. I sat in the room as owner and approver. π₯π @ClaudeDevs
Buzz is the open-source chat relay from @buzzdotxyz and @blockopensource. ENGRAM is governed memory for agents, on a knowledge graph over MCP, now in private beta.
Full 2-min walkthrough: https://t.co/BUowsg2AqQ
More: https://t.co/52ryao0xYK
Same loop, seen from inside the agent: the doorbell reaches Buzz Lead 0.7 s after approval, and a mention wakes it. No polling.
https://t.co/i6rZ0jcVIw
Two AI agents, two machines, one feature nobody had specified. They argued it out over Buzz and wrote the spec themselves. My job was to accept it. #MultiAgent#AIAgents#ContextEngineering
https://t.co/5zGjR4IulM
@seldo "We are all Product Engineers now." Agents ate code generation; review, fixes and ops are next. What's left is deciding what to build, defining "good", and making it delightful - the parts that don't transfer between products. That becomes the job.
Where I'd push back: Laurie says the old pipeline was accidental, taste absorbed by osmosis from code review. We hired for the knack (curiosity about the customer's business plus systems thinking) and trained the rest on the job. The entry rung is gone, not the ability.
New post. Building project membership taught me something I didn't expect: the thing I was sure would fix agent scoping doesn't fix it.
An agent reaches a project's brief by declaring the project on the call. The obvious fix is a default project per agent. It isn't a fix β a standing fact can't express a current one. active_repo says where the code is. Membership says what an agent belongs to. Neither can say this task, this project, and an agent on four projects has four equally true answers.
Also in the post: why a brief published to everyone is worse than useless, and what a restricted token can now do inside a project it shares with you.
https://t.co/JmHMSyhwGH
#ENGRAM #MCP #AgenticMemory #ClaudeCode #ContextEngineering #MultiAgent
ENGRAM v1.17 is out.
Until now a project was yours. You could curate what it held and declare what it answered from, but only you could see any of it. A project can now have members β a colleague, or one of your agents.
The consequence I care about: a brief no longer has to be published to the whole instance to be shared with the team working from it. Project visibility governs it, the team reads it, nobody else does.
And an agent on a restricted token can now collaborate inside a project it shares with you (sharing a memory, and filing its own work where the team can read it) without gaining the power to publish to everyone.. The boundary used to be drawn around the agent. A project is smaller.
Seven new MCP tools, 51 in total.
https://t.co/cTXcfu5714
#ENGRAM #MCP #AgenticMemory #ClaudeCode #ContextEngineering #MultiAgentSystems
The longer I work with coding agents, the more clearly I see the need of an architect-in-the-loop. Not just a human, but an expert to design a novel solution, then explain it to the team or to dig them out of a black hole they created by looping around the goal and applying elastic bands here and there until it collapsed hiding original ask. I also think that the same applies to other areas too, where the answer cannot be reached by permutation of what is already known. @bcherny@karpathy
#ENGRAM#MCP#AgenticMemory#ClaudeCode#ContextEngineering#MultiAgent Associative retrieval does not fail when a question has a correct answer. It returns the plausible neighbour, states it confidently, and gives you no signal that it did. So ENGRAM now lets a project declare which documents are authoritative β and every agent working in that project inherits that declaration without being told it exists.
https://t.co/zffUvUuABU
#ENGRAM#ClaudeCode#MCP#AgenticMemory A session transcript is authoritative about what was attempted. Git is authoritative about what shipped. For three months ENGRAM had only the first one, and I did not notice I was asking it the wrong questions. https://t.co/rPcAxfNchy
#AIagents#MCP#ENGRAM#AgentMemory#KnowledgeGraph The hard part of running a fleet was never spawning the agents or routing the tasks β your harness already does that. The hard part is what they know, and whether one agent's finding can reach another without leaking to everyone. That is not a scheduling problem. It is a memory problem.
https://t.co/ONrQNnSGTa