Skip to content
@theagentplane

agentplane

AgentPlane

AgentPlane

The layer AI agents need underneath them.

Website


Frameworks move fast. Agents are going to production before the infrastructure to operate them exists. The industry spent decades building reliability primitives for services — observability, cost governance, regression testing. For the agentic stack, that work is just beginning.

We build that layer. Open source, shipped in the open as we learn.


🔍 The problem

A production agent fails mid-run. The prompt, state, and tool chain that caused it are gone.

A multi-agent workflow burns 10× its token budget because each agent caps spend locally.

You ship a fix for a regression — but without a committed test, nothing stops it from coming back silently.

Monitoring built for stateless services doesn't transfer. Testing frameworks built for deterministic code break on probabilistic outputs. Something purpose-built for agents is needed.


📦 Projects

Record-and-replay for agent decision graphs.   pip install agent-chronicle

Chronicle instruments every LLM call, tool call, and routing decision as an immutable Envelope. When something breaks in production, that incident becomes a committed regression test — replayable without a single live model call.

Run-aware token governance for multi-agent systems.   pip install agent-tokenops

TokenOps governs the run, not the request. A shared ledger and control plane enforce spend policies across every agent, model call, and tool hop in a workflow — before the next LLM call executes, not after.

Chronicle and TokenOps compose: Chronicle records decision boundaries; TokenOps attaches as the cost and governance observer on live crossings.


🔭 What comes next

Chronicle and TokenOps solve two problems we hit first. The agentic stack needs more:

  • Memory that doesn't hallucinate past state and survives context windows
  • Evaluation built for behavior, not output strings
  • Retrieval that gives agents accurate, scalable perception of large codebases
  • Observability at the workflow level, not the request level

We're building in that direction and publishing the thinking as we go.


📝 Writing & talks

🎥 Your Agent Failed in Prod Why replayability beats bitwise determinism — Chronicle walkthrough
✍️ Your Agent Failed in Prod The nondeterminism problem and what record-and-replay actually gives you
✍️ From Validating Code to Evaluating Behavior Why traditional testing assumptions break for agentic systems
✍️ Why Agents Forget How memory works in AI agents, and what it takes to make them learn
✍️ Beyond Prompt Caching AST-aware indexing, multi-modal search, and codebase perception for coding agents
✍️ Spec-Driven Development Token economics and when structure helps vs. becomes tax for AI agents

All writing and talks → theagentplane.github.io/media


Built by Susheem Koul and Tisha Chawla  ·  MIT licensed  ·  Python 3.10+

Issues and PRs welcome on any of our repos.

Pinned Loading

  1. chronicle chronicle Public

    Record-and-replay for agent decision graphs: reproduce a prod agent failure as a committed regression test, and re-run your fix without live LLM calls.

    Python 7 1

  2. tokenops-wiki tokenops-wiki Public

    Python 3

  3. tokenops tokenops Public

    An operational field guide and reference architecture for treating tokens as a first-class infrastructure resource. Built for AI Engineer World's Fair 2026.

    Python 3

  4. theagentplane.github.io theagentplane.github.io Public

    JavaScript

Repositories

Showing 6 of 6 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…