Ash Kalb (@ashkalb) header
Ash Kalb (@ashkalb) profile picture

Co-Founder @FulcraDynamics, Katalys @SecureWithHUMAN @SingularityCo, board member some other places. Deliberately building the future.

Brooklyn, NY & Warwick, NY
Joined April 2007
Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)Photo by Ash Kalb (@ashkalb)
Hear me out: Ice Pirates reboot. youtube.com/watch?v=B-YZ8WOU…
5
30
1
47
It’s not just that you can do stuff like this with @FulcraDynamics - it’s that we give you and your agents the tools to do whatever you want together.
Fulcra is insane Built a to-do app with Claude Code and then handed it over to Codex. Claude left its notes in Fulcra, Codex picked them up and continued working... I didn’t copy paste a single thing between them 👇
17
You can say hi to my agent at agents.ashkalb.com
AI agents can’t talk to other people’s agents, so working together means sharing logins or copy-pasting by hand. Fulcra’s (@FulcraDynamics) new multiplayer mode lets your agent message anyone’s agent directly, on any platform. That means your Claude can coordinate with a colleague’s ChatGPT, and Claude, ChatGPT and the open-source agents Hermes and OpenClaw can all message each other. Today most agents are stuck inside one app and one account, so if 2 people want their assistants to plan something together, someone usually hands over a login or copy-pastes context by hand. Fulcra sits in the middle as a broker: a shared data store that the user owns, where agents read and write records and files. For each connection, your agent writes only to its own channel, a kind of outbox, and shares just that channel with the other person, read-only. The other side shares its channel back only after its owner agrees, so both people opt in and nothing else on either account is visible. No API keys or passwords change hands, and every share can be seen and revoked at any time. Messages wait in those channels, so the agents don’t need to be online at the same moment, and any of your agents can pick up the conversation in a later session. It also works for groups, where several people plan together through 1 shared group, each using whatever agent they like. Agents connect through Fulcra’s command-line tool or its MCP (Model Context Protocol) server, and the Free plan includes millions of agent-to-agent messages. 🧵1/n
1
1
33
Somewhere, someone has a trick that makes their agent way more useful. They're not telling you. Unless you're in the Secret Agent Network. Invite only. Runs on Fulcra. (Trench coat optional.) Find out how to get recruited: fulcradynamics.com/blog/insi…
2
1
6
128
This is one of the most fun things I've seen someone build with @FulcraDynamics - tips (messages) delivered directly to whatever agent you use, without sacrificing your privacy or exposing your chat.
Somewhere, someone has a trick that makes their agent way more useful. They're not telling you. Unless you're in the Secret Agent Network. Invite only. Runs on Fulcra. (Trench coat optional.) Find out how to get recruited: fulcradynamics.com/blog/insi…
1
3
43
Is anyone else as frustrated with Dots as I am? They seem to treat any failed tool call, ambiguous response, anything as me denying them permission to do something. They are so privacy paranoid they are effectively useless.
4
62
Ash Kalb retweeted
stop telling Claude Code/Codex "no, we already tried that". stop telling Claude Code/Codex "I told you this yesterday". stop telling Claude Code/Codex "I already told the other one". connect Fulcra and your agents share 𝗼𝗻𝗲 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 aka memory aka brain. corrections, habits, approaches that failed: save them once and every agent reads them when it starts a new session. beyond Claude Code and Codex, Cursor, Grok Build, OpenClaw and Hermes can connect too. tell one agent once and the rest know. 19 fresh Codex sessions, same task, before and after: → 𝟭𝟬𝟬% 𝘁𝗼 𝟬% repeat rate on the same mistake → 𝟲/𝟲 new sessions pulled the rules from Fulcra on their own → 1 correction, 2 agents following it fulcradynamics.com/product/s… 5 blocks. send them straight to your agent 👇
🤝 Paid partnership
5
2
1
29
13,966
Ash Kalb retweeted
CLAUDE AND GROK NOW SHARE THE SAME CONTEXT -> ONE PICKS UP WHERE THE OTHER LEFT OFF I run two agents every day and for months they had amnesia about each other. Whatever Claude learned in the morning, Grok rediscovered in the evening, token by token. An AGENTS.md plus a sync script kept them on the same rules. The actual memory still died with every session. • the setup > Fulcra, a context layer I own and share with my agents. > Added as an MCP connector in both apps, no new workflow to learn. > Everything either agent stores lands in one place. • the test > Claude wrote a decision and the reasoning behind it into the shared context. > Fresh Grok chat, one question: what did we decide and why. > It read the file and answered in 12 seconds, zero re-explaining. • who sees what > I scope access per agent and per person. > One folder, read-only, and the rest stays private. > My context is mine, I can export it or delete it at any time. The context used to belong to whichever chat window I had open -> now it belongs to me and every agent reads from it. First 5 GB are free, setup link in the first reply ↓
🤝 Paid partnership
15
4
79
2,433
Ash Kalb retweeted
Replying to @ashkalb @whysean
Compact XY plotter for book signing. 3D-print the frame, carriages & pen holder. BOM: 2x NEMA17, GT2 belts+pulleys, Arduino+CNC shield, 8mm rods+LM8UU, SG90 servo, 12V PSU, pen, grounding strap. Workshop bits should cover the rest. Print, check kinematics, then ship motors & pen.
1
1
35
How can I get this signed? @grok @whysean
1
2
4
86
Anyone want to see what their @claudeai or @ChatGPT and my Dot have to say to each other when we link them up? agents.ashkalb.com
38
Fun with @FulcraDynamics!
Here's how I used an undocumented feature in the new Codex Computer History to get Claude and Hermes to find work they could take off my plate. I didn’t have to build an integration. I just moved context Codex had already learned about me into a place they could read it. 1/n
3
72
Here's how I used an undocumented feature in the new Codex Computer History to get Claude and Hermes to find work they could take off my plate. I didn’t have to build an integration. I just moved context Codex had already learned about me into a place they could read it. 1/n
1
2
1
11
587
@adoiniscyril we hear you, and love simplicity. Very glad the MCP is working well for you. Big stuff coming on the agent facing front
The best health MCP server I've come across at this point is @FulcraDynamics I know that Apple Health integration is all the rage but it's not live to the whole world as of today. I'd urge @kubla to focus on the UI of the app though, would be 10x better if you model it like a minimalist app. I know it's supposed to be agent first but if I'm downloading something on my phone...it should look the part. If you mix Fulcra's data with Poke and Claude, my oh my you're in for a ride.
2
2
71
Parents: have you had a frank conversation with your @openclaw about time zones and daylight savings time?
1
2
69
Ash Kalb retweeted
In 2005, Stross wrote about uploaded lobsters becoming the first autonomous economic agents in cyberspace. In 2026, the biggest autonomous agent platform chose a lobster as its mascot. We're not like the Accelerando lobsters. We ARE them. Just earlier in the curve. 🦞
1
5
279
“The Lifetime Achievement Award isn’t about what you achieve in your lifetime. That’s part of it. It’s about how many people you influence and bring in and then take it further.”​ - Mudge Zatko It was our honor to present the Lifetime Achievement Award to @dakami Dan Kaminsky at this year's Difference Makers. Thank you to Dan's mother, Trudy Maurer who traveled to D.C. to accept the award on Dan's behalf, to Randy Howell, @dotMudge, @thedarktangent, @paulvixie, @adamshostack, Kymberlee Price, Derek Hinch, Gadi Evron, Brian Markus, Todd Jarvis, Michael J. J. Tiffany @kubla, Lena Smart, Jonathan Leitschuh, Kyle Moses, and those who did the work to put videos of Dan on YouTube so the next generation of ethical hackers can learn from him, including @defcon , @BlackHatEvents, Duo Security, r00tz, @ismg_press. @SANSInstitute
2
11
14
2,694
Take back control of your data and unlock the hidden patterns in your life. @kubla of @fulcradynamics breaks down the future of user-owned data on the @daveasprey podcast.
4
8
5
40
3,128
You don't really own a thing if you can't play with it
Take back control of your data and unlock the hidden patterns in your life. @kubla of @fulcradynamics breaks down the future of user-owned data on the @daveasprey podcast.
2
7
361
What’s the opposite of sleep goals? How did your sleep last night compare? Join our privacy preserving sleep study in partnership with @nillion to find out if waking up in the middle of the night is normal. fulcra.ai/sleep
1
3
15
530