Chris Chabot
Chris Chabot, Member of Technical Staff, building agent platforms
Getting an agent through a demo is the easy part. I design and build the infrastructure required once agents run unattended and other teams rely on the platform: runtimes and orchestration, SDK contracts, memory, permissioning, and the evaluation and verification that gate releases.

Selected work
Verifying a coding agent port without a model in the loop
A production coding agent of about 340,000 lines of Python, built by my colleagues, moved to TypeScript with one requirement: byte-identical behaviour in everything not specific to the new platform. I designed the method and directed the agents: a formal model, a checklist generated from the syntax tree, clean-context review, then replay.
designed, directed, reviewed, verified
Putting scripts in charge of agent-run releases
Releasing an agent-native cloud platform: scripts decide what ships and agents diagnose what failed, the experience an agent has building on the platform is benchmarked and gated like a latency budget, and the largest tenant is reshaped to fit the platform rather than the limits raised.
designed, verified, operated
Enforcing wire, identity, and approval contracts in an agent platform
What crosses a boundary has to be checkable data: wire formats, delegated identity and single-use approvals verified where they are used, across five language SDKs, and shared code copied with signed provenance instead of pulled through a dependency chain.
designed, led
Proving the harness before scoring the agent
Before asking whether a change helped an agent, I want to know whether the comparison actually contains the change. The tooling here treats each run's configuration as a claim to be checked, and keeps corrections beside the original record rather than over it.
designed, built
Getting an agent coordinator to brief like a product manager
What changes when a coding conversation becomes a project that keeps running while you are elsewhere, and what a coordinator and its workers need in order to stay useful when there are a hundred of them.
designed, directed
Replaying injected memory without breaking extended thinking
Agent memory has to enforce tenant isolation, surface current facts over stale ones, and stay within the latency budget of the next reply.
designed, built
Letting an agent diagnose production without giving it a shell
Agents work best with broad, redacted reads and narrow, reversible writes: a view of production they cannot damage, guardrails kept off the hot path, and a browser whose unboundable parts stay switched off.
designed, built
Public code
codex-swift
OpenAI’s Codex ported to Swift as a supervised, Seatbelt-sandboxed macOS service.
mem0 in Rust and TypeScript
Rust and TypeScript ports of Mem0’s core agent-memory pipeline.
open-cloud
Cloudflare-shaped Workers and storage bindings running locally on Bun.
code-search
Rust code search with BM25 lexical ranking and structured output for agents.
Conquer
Playable Godot RTS built on a fixed-point simulation for lockstep LAN play and replays.
Earlier products, open source and standards
Apache Shindig for PHP
Chief author of the PHP implementation of the OpenSocial container; PMC member and committer.
built, from 2008
OpenSocial
A common API for social applications across participating networks.
co-authored, contributed, from 2007
Portable Contacts
A simple XML and JSON protocol for address books and friends lists over HTTP.
co-authored, 2008
OAuth 2.0
The framework for granting applications limited, scoped access to an HTTP service.
contributed, 2012
OpenID Connect
An interoperable answer to "who signed in?" on top of OAuth 2.0.
contributed, 2014
Google+
Founding member of the project; led the platform's developer launch and API ecosystem.
contributed, led, from 2010
Latest writing
Deterministic wakes, reports, and memory for long-running agents
How deterministic code can own wakes, reports and memory for long-running agents, with event batching and cold resets timed by the prompt-cache lifetime.
SelectedOrchestrationMemoryAgent systems
Keeping agent guardrails off the hot path
How to keep an agent's guardrails off the hot path: four ordered checks, a judge that never sees untrusted text, and owner interruptions budgeted like latency.
SelectedSecurityAgent systemsPerformance
Designing out shared fate in an agent runtime
Why process-per-agent is affordable once idle agents unload, how to fence a single SQLite writer, and why a plan that resends history makes the cached prefix the cost model.
RuntimeStoragePerformance
Treating a sixteen-agent build like a production system
Running a sixteen-lane agent build like a production system: reviewing specifications at their seams, a rival design as adversarial review, and measuring friction from session logs.
OrchestrationAgent systemsPerformance
Moving a cloud coding agent to a Mac with consumer-driven contracts
Running a cloud coding agent on one Mac by building shims from its call sites, mirroring upstream unedited, and reviewing each change from the goal and diff alone.
PortingRuntimeVerification
