Al Baker

20 years ago at Bell Labs, we spent a lot of time reviewing Jini and JXTA. Today, we started Bad Monkey, Inc and fixed them. It's called AgentSpaces, P2P fabric for agent and service collaboration. #Embabel, #SpringBoot, #SpringAI integration. github.com/badmonkeyai/Agent…

Autonomous P2P agents, meet @deno_land’s celld. ⚡️ AgentSpaces now brings decentralized agent and asset coordination to self-hosted Durable Objects. Build self-organizing AI agent fleets across the browser, Node.js, and private edge VMs w/ e2e encryption, CBOR (RFC 8949) messaging, NAT traversal, and multi-protocol fabric built-in (mTLS, DTLS, WebRTC, WSS,.. ). Check out the repo: github.com/badmonkeyai/agent… Docs: badmonkey.ai/agentspaces/dev… cc @rough__sea @biwanczuk @calvinfo @feross

At Bad Monkey, we're working on intelligent event processing, leveraging AI on all those real-time events, so you can react to what's happening now.. not later, not after the data winds up in the cloud, and a job gets run. We started with ISR and made an automated tracking solution that is 100-10,000 faster than others. Can't wait to show Project Agincourt and @SecWar what we're doing with C2, autonomy, and UxS.

AgentSpaces 0.3.0 is out: shared objects for fleets of AI agents, peer to peer, no broker. 9,000 downloads in week one. LangChain4j, Spring AI, Micronaut, Python, TypeScript, all updated. New: fan-in joins, votes in three methods, running totals, reducers, tags support. Peering protocol 10x efficiency. github.com/badmonkeyai/Agent…

By end of day 1 of AgentSpaces we had 28 companies, 1100+ downloads, rocketed up near the top of popular open source packages on Maven Central. By end of week 1, added support for LangChain and Micronaut. Next week, will be plugins for Claude and Codex, and integration with the Bad Monkey intelligent event processor (IEP). github.com/badmonkeyai/Agent… -- come talk to us at #AUSA2026 and learn more!

Couple more ways to add peers into your AgentSpaces P2P fabric. agentspaces-micronaut, and inspired off of the langchain work there, also agentspaces-langchain4j. See github.com/badmonkeyai/agent… and github.com/badmonkeyai/agent…

Use AgentSpaces replicated tuple space, with Spring AI. With memory.enabled, the worker's conversation lives in a replicated space too. SpaceChatMemoryRepository is a Spring AI ChatMemoryRepository that writes each save as the conversation's next leased snapshot and retires the older ones, so an abandoned conversation leaves the space on its own and a snapshot over 64 KiB travels content-addressed. FleetChatMemoryAdvisor keys the conversation by the in-flight take's entry id by default. #springAI #AgentSpaces #P2P

When we built AgentSpaces, we wanted polyglot replicated tuplespaces and P2P services, so there's an open spec (CBOR, mTLS, etc), so we added support for Python, Typescript, and Clojure. More to come. badmonkey.ai/agentspaces/dev… Check it out on Github to build P2P fleets

.@springrod would love any feedback on the Embable integraiton, expanded the blackboard concept into a replicated TupleSpace, and the GOAP planner can now see actions across the P2P fleet, including A2A gateway. Version 0.2.0 on github. badmonkey.ai/agentspaces/dev… -. .

@starbuxman @springjuergen would love any feedback - see Spring AI integration: badmonkey.ai/agentspaces/dev… and all wrapped up nicely with a Spring Boot starter: badmonkey.ai/agentspaces/dev…

We're headed to Gartner Data & Analytics Summit in Orlando next week, see Voicebox chat with multiple data sources: most business user friendly #GenAI solution #gartnerda - stardog.ai -- oh and spots still open for executive get together info.stardog.com/talk-to-you…

We just launched Voicebox - get LLM query answering over your enterprise data, without hallucinations, with enterprise security and all the rest of the features you care about in business. Checkout stardog.ai #LLM

One of the best parts about working at Stardog is that I'm surrounded by subject matter experts across a variety of fields. Started the day with machine learning and vector algorithms, finished the day with platform automation

Unpopular opinion -- the touchbar on the macbook pro is pretty neato 😁

the Transducer talk on generalizing reducing algorithms to transformation is one of my favorite talks, and approaches to think about when decomposing problems