Software / Pollard

Pollard.

A runtime for agent work with explicit resource limits, approval gates, inspectable execution trees, and replay.

Agent infrastructure

Govern each step of agent work.

Pollard records model and tool calls in a content-addressed execution tree. Keep your application’s model clients and agent loop while adding explicit controls at the call boundary.

LIMIT

Bound the work

Set token and step allowances, refuse work that exceeds known limits, and share resource scopes across workers. Branches and delegated assignments carry their inherited constraints.

GATE

Control actions before execution

Resolve tool calls against versioned action definitions. Policies can allow, refuse, or require approval; delegated permissions can narrow as tasks pass between agents.

REPLAY

Inspect a recorded run

Use stored semantic steps to audit a run and replay recorded results in tests. Branch and rollback operations preserve the recorded history while you explore alternatives.

Packages / November 13, 2026

Choose a language runtime.

Python, TypeScript, and Rust have independent release versions. The native TypeScript and Rust releases target Python 1.6.0 runtime behavior; Python 1.6.2 includes the optional Codex CLI adapter.

PYTHON · 1.6.2

pollard

Install with pip install pollard. Includes agent teams, inherited scopes, checkpoints, durable approvals, and optional Codex CLI task integration. Python 3.10 or newer.

TYPESCRIPT · 0.2.0

pollardai

Install with npm install pollardai. The native Node.js runtime supports streaming, replay, persistent stores, shared resource limits, provider adapters, and audit tools.

RUST · 0.2.1

pollardai

Install with cargo add pollardai. The native Rust runtime includes eight storage backends, async streaming, shared resource limits, replay, and audit tools.

Build with Pollard

Begin locally, then connect your tools.

The Python quick start uses an ordinary local function, so you can inspect a governed run before connecting a model provider.

FIRST RUN

A small execution tree

Install the Python package and follow the credential-free example. Create a runtime, set a token and step allowance, invoke a local model callable, and inspect the resulting node and usage report.

DELEGATION

Give each agent a scope

Build a team with recorded task identities and separate cursors. Delegate work with inherited resource limits and narrowed tool permissions, then inspect dependencies and results together.

CODEX CLI

Record and replay a coding task

Python 1.6.2 adds an optional adapter for Codex CLI tasks. Record the task inputs and returned answer, apply execution controls, and reuse the stored result through strict replay.

Research and materials

Governed semantic execution trees.

The paper connects agent control, audit records, and replay across frameworks.

IEEE ICTAI 2026 · ACCEPTED PAPER

Pollard: Governed Semantic Execution Trees for Framework-Independent AI Agent Control and Replay

Muntaser Syed and Marius Silaghi. Presented November 3, 2026 at IEEE ICTAI in Boca Raton. Preprint: arXiv:2610.16145.

WORKING EXAMPLES

Swarm Forest and ReleaseProof

Swarm Forest explores governed agent teams with shared limits and drift detection. ReleaseProof connects evaluation results, approval, execution controls, and drift holds in an agent-release workbench.

Talks and workshops

Learn through practical sessions.

Conference sessions connect the runtime to governed agent workflows and open-source development.

DEVFEST TAMPA · NOVEMBER 14, 2026

Govern Your Agents: Budgets, Approval Gates, and Exact Replay with Pollard

A hands-on workshop at DevFest Tampa 2026: Build, Secure, Scale, at USF Tampa Campus, Engineering Building II. Exercises cover resource limits, action approval, evidence verification, and strict replay.

DEVFEST MIAMI · DECEMBER 5, 2026

Build a Creative AI Agent You Can Budget, Inspect, and Replay

An accepted hands-on Python workshop at DevFest Miami 2026: AI + Art Edition, at Mana Tech Loft 10.

HACKTOBERFEST ORLANDO · OCTOBER 22, 2026

Shipping the Pollard Ecosystem

A practical session on packaging, testing, documenting, and releasing Python, JavaScript, and Rust libraries, illustrated with tokenmaster and Pollard.