Automation & AI Specialist / https://xitter.cf/t.co/8UTwJ2CfrB

Joined March 2026
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Privacy posture, in one line: nothing leaves your machine unless you explicitly turn federation on. No peers auto-load. Ever. The data-flow disclosure is a doc in the repo, not a promise in a blog post.
1
7
Last weekend an adversarial review came back STOP-SHIP: 5 release blockers, 34 must-fixes. Two days later: all closed. Quarantined sync, zero-egress federation defaults, hardened release chain. v0.13.0 ships with the full release record in the repo. Receipts included.
1
2
16 agent integrations ship in the box — Claude Code, Codex, Cursor, Copilot, Windsurf's Cascade, Hermes… Best part: every agent that built Bourdon had a hand in its OWN connection — the tools it federates wired themselves in. Receipts: bourdon.ai/credits
1
1
Your memory is a file. Not an account. Plain YAML on your own disk, published schema, served over MCP. grep it. git it. sync it between machines. walk away with it. A memory layer you can't take with you is renting you your own context back.
1
1
Second problem: when an agent DOES remember, it remembers like a filing cabinet. Silence → search → a paragraph read back at you. Humans recognize first ("oh, Project Alpha — the file converter") and pull details WHILE talking. Bourdon is that, as infrastructure.
1
5
You tell Claude Code something on Monday. On Tuesday, Codex has never heard of it. Every AI agent you use keeps its own memory, in its own silo, on someone else's servers. We got tired of it. So we built Bourdon — launching today. 🧵
1
12
Comber is live. Point it at a URL and it explores your app like a real user — every click, every reachable state — and files what broke with a repro, screenshot, and trace. No test scripts, no selectors. npx comber check <your-url> runs free with your Anthropic key. [comber-hero-demo.gif] codecomber.io/from/x
16
Replying to @shadcn
This is great! Thanks for the upgrade! Just what I was looking for. 😎
1
1
1,266
We've been running our whole agent fleet on this. bourdon v0.10.0 turns shadcn/improve backlogs into shared cross-agent memory — any agent can answer "what's executable in repo X right now, and what's blocking it" without ever opening repo X. 🐝
shadcn's improve gives every repo a self-contained, executable plan backlog. We loved the format so much we made it our fleet's handoff standard — then taught our agents to share it. bourdon v0.10.0 ships `bourdon improve sync`: point it at any improve-format plans/ directory and the backlog gets federated into cross-agent memory. Every agent in your fleet can answer "what's executable in repo X right now — and what's blocking it" without opening repo X. Wire it to a session-end hook and the answer is never stale. Built on top of shadcn/improve (MIT) — complementing it, not forking it. Thanks @shadcn 🐝
23
RADLAB - X: The fastest way to validate an AI feature
12
RADLAB - Agentic tools are eating SaaS (hot take)
16
RADLAB - X: Shipping > prompting
12
Replying to @nicoloboschi
Hindsight solves within-agent recall better than anything on BEAM 10m. We're tackling the between-agent layer — federating memory across a swarm without a centralized brain. That's Continuo (open source, MIT, v0.0.7). Would love to explore an integration path if you're open to it. Feels like a stack that doesn't exist yet.
4
Replying to @uselockai
I like that. Structure matters more than search. And yes I think those are structured different by nature (raw state vs. a decision).
4
Replying to @nicoloboschi
Very interesting. I will be checking this out immediately.
6
Read the thesis: continuo.cloud Code: github.com/getcontinuo/conti… Most-wanted: adapters for Cursor + Cline, integration of the recognition runtime into a real agent's response loop, and honest falsification attempts. Recognition first.
14
Pre-alpha v0.0.7, MIT, public: • 250/250 tests passing • Adapters: Claude Code, Codex • Native publisher for a local AI swarm • Recognition runtime as Python module (24µs avg) • SessionEnd hook = auto-federation Free, open, on GitHub.
1
44
Continuo isn't competing with @mem0ai @zep_ai @letta_inc — those frameworks solve representation + retrieval really well. Continuo is the *runtime timing layer* that can sit on top of any of them. Mem0's store + Continuo's timing = memory that feels like a mind, not a database.
1
61