Pi Durable lets agents survive crashes and run anywhere

Earendil shipped Pi 1.0 and, alongside it, an experimental harness called Pi Durable for long-running agents that run anywhere. It opens over memory, SQLite, or JSONL storage, checkpoints every task so a dead process resumes where it left off, runs many conversations concurrently, and lets extensions plug in tools, prompts, and hooks. The whole source is about 15,000 lines, small enough for an agent to read.

If the process dies, a new process opens the same storage, finds the unfinished tasks, and continues each one from its last checkpoint.
  1. lukebuehler

    Very cool to see Pi build a durable agent harness too. I've been building in this space for quite some time myself [0][1] and it is a super interesting place of innovation. Less hype-y that on-your-machine coding agents, but all major players are building products in this space: LangChain Deep Agents, Vercel Eve, OpenAI Agents API, Anthropic Managed Agents, etc.

    The main reasons are:

    1) they are "durable", i.e. easier to make long-running in an unattended way, and easier to implement recovery, monitoring, etc

    2) separating the harness from the compute brings safety and scaling benefits

    3) easier to make multi-player.

    [0] https://github.com/smartcomputer-ai/lightspeed

    [1] https://github.com/smartcomputer-ai/agent-os/

  2. lemming

    One decision here which seems like a large break from the original pi is that Durable doesn't support branching conversation trees, it only supports conversation forks with ancestry information. Can anyone speculate (or confirm, if you happen to be Armin or Mario) why this is, and if that is necessary for the durable guarantees? The branching conversations are still an immutable data structure, so I can't see why this would be necessary, but perhaps I'm missing something.

  3. ireadmevs

    > The entire source code, without tests, is about 15,000 lines, which comes out to about 150,000 tokens with GPT and about 250,000 with Claude.

    Woah, that big of a difference when it comes to token counting?

  4. zmmmmm

    It's an interesting concept. This is half way to replicating pieces of Gastown. I like the idea, but I'm disappointed these tools still fail to address sandboxing as a first class citizen. I want to be able to declaratively set rules for what sandboxes agents execute in and mark context as tainted when untrusted etc. So far I still don't see any of these harnesses properly addressing this space. I'd be interested in knowing if it can be done through the extensibility of Pi, but since it operates directly on the trust layer, it feels like the type of thing that really needs native support.

  5. phainopepla2

    What are people using these infinitely-running agents for?

More from this day

2026-10-01