Open Source · Built from Inside City Hall

The AI harness for local government.

The AI industry is building infrastructure to run agents. We are building the accountability layer local government needs to run them responsibly. CivicWork is building CivicAide, an open-source governance layer that gives municipalities the tools to deploy AI on their own terms. Not a vendor. Not DIY. A partner for cities ready to own their infrastructure.

Learn About CivicAide →
Where We're Focused
The Challenge

A capacity crisis, a data problem, and a vendor dependency that nobody talks about.

The same planner reviewing a 47-page environmental impact study is also answering phones, attending three committee meetings, and trying to update a comprehensive plan that's been outdated since 2018. The expertise is in the building. The hours aren't.

Meanwhile, the data that should power better decisions sits scattered across systems that don't talk to each other, half of it in PDFs from 2011. Vendors build products around this public data and charge municipalities to access their own information. A mid-size city pays $14,000 a year for public records request software, a system that is, at its core, a form, a queue, and a deadline tracker. Twenty thousand municipalities can't afford even that, and manage a legally mandated process through email and spreadsheets.

Car manufacturers started sealing components and requiring proprietary tools. Not because the work got harder, but because open access threatened their margins. That tension created Right to Repair. Municipal software followed a similar path, with one difference: the underlying technology was never proprietary to begin with. The databases are open source. The hosting is commodity cloud. The complexity is largely manufactured.

Cities now have access to AI that can function as on-demand analysts, researchers, and software developers. The gap between what gets charged and what it costs to build is collapsing. This is a moment for more openness, more modularity, more choice. CivicWork exists because cities deserve those choices.

AI will change how municipal work gets done. Agents are coming, and most local governments aren't ready. Not because they lack ambition, but because their data layer wasn't built for it. CivicWork exists because cities deserve those choices, and to make sure those decisions are made by cities themselves, deliberately and transparently, not dictated by vendor roadmaps.

Capacity gapsFragmented data systemsVendor lock-in on public dataNo path to agent-readiness
The Harness

CivicAide: the governance layer the AI industry isn't building.

The agent harness infrastructure is maturing fast. Anthropic, OpenAI, and the open-source community are building the core: context management, tool access, execution orchestration. What none of them are building is the accountability layer local government requires. CivicAide builds on that industry infrastructure and adds what's missing: decision traceability, public records compliance, and governance guardrails designed for democratic accountability, not enterprise software.

Building now

Agent-Ready Data

Before any harness or governance layer can function, municipal data must be agent-ready: normalized, structured, and accessible in open formats. Budgets, permits, minutes, zoning records, pulled out of PDFs and vendor silos into something an agent can actually read. This is foundational work no vendor has an incentive to do.

Building toward

The Governance Layer

Decision traceability, verifiability questions surfaced in context, Trust Stack as a lens on what each decision actually needs, FOIA-compliant logging, and authority-mapped approval workflows. The accountability infrastructure that makes it possible for a city to say yes to AI, because every output is traceable and every decision point is logged.

PolicyAide in testing

Applications

PolicyAide is the furthest along: multi-agent policy analysis that pressure-tests proposals before they reach a decision-maker. Built on Anthropic’s Agent SDK, it demonstrates what becomes possible with governance infrastructure in the design. The Municipal Plugin and Coda MCP Server are live and open source. Vendor contract analysis is in development.

Open SourceAuditable · Explainable · Designed for public scrutiny
Explore CivicAide in depth →
Frameworks for Saying No

Most AI vendors sell what's possible. We start with what's appropriate.

Before building any tool, we ask two questions: Can we verify that it works? And does deploying it build or erode the trust a community needs? Together, the Verifiability Framework and Trust Stack form a diagnostic system for responsible municipal AI.

Framework 01

The Verifiability Framework

One question: Can we verify this? If you can define success criteria and automatically evaluate outcomes, the task is an automation candidate. If you can't, AI should augment human judgment, never replace it. And when a use case is mixed, decompose it, automate what you can, keep humans on the rest.

Verifiable → Automate

Permit completeness checks, document classification, data validation, compliance verification. Clear criteria, fast iteration, measurable outcomes.

Mixed → Decompose

311 triage, public chatbots, hiring, inspection scheduling. Separate the automatable components from the parts requiring human judgment.

Non-verifiable → Augment only

Budget priorities, policy tradeoffs, community needs, accountability decisions. AI expands what you know. Humans retain authority over who decides.

Read the full framework →
Framework 02

The Trust Stack

Four layers of trust, each building on the last. Layers 1–2 are built with technical tools: audits, testing, metrics. Layers 3–4 require democratic process: deliberation, community input, accountability. The common failure: trying to solve Layer 3–4 problems with Layer 1–2 tools.

01
Process TrustTechnical
Did it follow the rules?
02
Outcome TrustTechnical
Did it work?
03
Representation TrustDemocratic
Does it reflect us?
04
Sovereignty TrustDemocratic
Do we still control this?
Read the full Trust Stack →

“AI should expand what you know, not replace who decides.”

These frameworks give municipal leaders structured language for evaluating AI proposals, and principled grounds for declining when a deployment doesn't fit, without sounding like they're against technology.

Currently partnering with U.S. Digital Response (USDR) on AI use case discovery across Elgin city departments, using the Verifiability Framework and Trust Stack as diagnostic tools to identify where AI helps and where it doesn't.

Built From the Inside

“I started building CivicAide because I needed it. A part-time councilmember with a day job, trying to get through 200-page packets before the next vote. It was a Coda doc connected to a few LLMs. Then frontier models got good enough to do real policy analysis. Then agent frameworks matured enough to orchestrate it. The tools kept getting better, so the ambition kept growing.”

Dustin Good is a sitting at-large city councilmember in Elgin, Illinois, second term, 4.5 years in office. CivicWork grew out of the problems he encountered firsthand: too much data, too little time, and a growing conviction that local government shouldn't have to wait for vendors to solve problems practitioners already understand.
4.5 yearsin elected office
2 termsas at-large councilmember
SpeakerIML & City AI Connect conferences
Our Approach

How we think.

01

Practitioners first

This wasn’t designed from a research lab or a consulting firm. It was built from inside a municipal building: from the meetings, the packets, and the cross-departmental workflows that make local government actually function. The tools reflect actual workflow, not a theory of it.

02

Automation before AI

Not everything needs a language model. Sometimes a well-structured automation does the job. Just as important: CivicWork helps municipalities say no to AI where it doesn’t belong. Staff are getting pitched AI solutions for everything, and having a principled framework for declining, not out of fear but out of clarity, is as valuable as knowing where to deploy.

03

Own the data layer

When a municipality wants to leave a software vendor, they often discover their own data (years of records, workflows, and institutional knowledge) can’t come with them. Agent-readiness means making public data accessible, portable, and structured, not just for humans, but for the AI tools that will increasingly help staff do their jobs. That’s not a technology problem. It’s a data ownership problem, and it’s what we’re building toward.

04

Build on the best, contribute what’s missing

We don’t rebuild what the AI industry has already built well. The agent harness infrastructure is maturing and we build on it. What we contribute is the piece they aren’t building: the governance layer local government needs to use these tools accountably. Open source means inspectable, auditable, and not dependent on a vendor’s continued existence. Currently built on Anthropic’s infrastructure and designed so cities are never locked to a single provider.

Open Source Tools

What's shipping now.

These tools exist today, are open source under Apache 2.0, and are usable by any municipality. They're the foundation we're building CivicAide on top of.

Claude Plugin

Municipal Governance Plugin

Eight skill modules for Claude Desktop and Claude Code: ordinance analysis, meeting prep, policy research, budget review, constituent communications, agenda packet synthesis, intergovernmental scanning, and vendor contract evaluation. Each module includes built-in analysis boundaries that disclose what a single AI instance can and can't responsibly conclude.

View on GitHub →
WebMCP + Chrome Extension

Municipal WebMCP

WebMCP configurations and a Chrome extension that give AI agents structured access to public legislative data. Covers Legistar (Granicus) meeting and legislation records and Municode (CivicPlus) codified law across 3,300+ municipalities. Public data should be easy to access programmatically, not just through a web browser.

View on GitHub →
Apache 2.0Free to use · Free to fork · Built for municipalities
Live Now

Your city council agenda, explained.

Council agendas are public documents. Understanding them shouldn't require a law degree. CivicBrief takes an agenda PDF and turns it into plain-language briefings you can actually use, in your language, in your preferred format.

Pick the items that matter to you, choose between a written summary, Q&A, audio, or visual format, and get a briefing built for residents, not attorneys. If someone already asked about the same item, it loads instantly from cache.

Try CivicBrief →
01
Upload or browse

Drop a city council agenda PDF or pick one that's already been uploaded from the library below.

02
Pick what matters

Select agenda items and choose your format and language.

03
Get your briefing

Plain-language summary, Q&A, audio, or a visual you can share.

Multilingual (English, Spanish, Polish) · Four output formats · Cache-first for instant results · AI-generated, always attributed

Let's build together.

CivicWork is looking for municipal partners willing to be early collaborators. If you're a municipality, a civic technologist, or building in this space, try a tool, run an assessment, or reach out directly.

Try CivicBrief →Run the Governance Assessment →Get in TouchView on GitHub