Booley

The open-source agentic RTL IDE

IDE

RTL development is fragmented across editors, tool-specific commands, build environments, logs, and waveform viewers. Booley brings that workflow together in one reproducible VS Code workspace.

• One typed Booley Flow surface: simulation, lint, synthesis, and FPGA implementation use one structured interface. A simulation Target selects the underlying EDA tool—Verilator today or Xcelium^* tomorrow, while the engineer and LLM agents use the same sim Flow either way (it is powered by FuseSoC). You don't have to maintain EDA glue scripts anymore.
• Reproducible team environment: configure the project once, and its Docker environment supplies the same pinned EDA stack, agent tooling, and system dependencies to every team member. Nobody has to rebuild the toolchain independently or debug "works on my machine" differences (why Docker).
• One IDE: RTL, the agent, terminals, EDA runs, results, and waveform viewing live in a single VS Code window. You can move from editing to simulation to waveform debugging to synthesis without switching between separate applications.

_{* Xcelium support is a work in progress.}

Built for agentic workflows

The mental model behind Booley is simple: treat an LLM agent like a talented junior engineer. It can write RTL and testbenches, but it is inexperienced with EDA tools, prone to questionable design decisions, and too risky to give unrestricted host access. Booley gives it a constrained workspace, explicit specifications, automated checks, and human review.

• Sandboxed for autonomous execution: the agent and every command it launches run inside a Docker container with restricted mounts and network access. You can delegate long-running tasks to agents without approving every bash tool call and without worrying about your files and git history (details, security model).
• Strict guardrails and acceptance criteria: in Ticket Mode, the Harness checks explicit acceptance criteria you define during ticket creation. At review time, one briefing shows scope deviations and configured checks—such as area or performance regressions and mutation score—so you can see at a glance what passed and what needs attention (details).
• Waveform-aware debugging: bwave lets the agent query real traces instead of guessing from RTL. Ask “How many i_ready/o_valid handshakes occurred between 1,000 and 2,000 ns?” or “When did data_o equal 0xDEADBEEF?” The agent answers from actual simulation data instead of spending minutes reasoning from code (and getting it wrong) (details).

There are two ways you can cooperate with LLM agents in Booley:

• Interactive Mode - you chat with Claude Code or Codex, tell the agent what to inspect or edit, which simulation or synthesis to run. You guide the work closely and make decisions as they come up. The agent already knows the project's Targets, tests, Booley Flows, and Specialists, so each chat starts ready to work.
• Ticket Mode - the autonomous path. You write a ticket, specifying what needs doing, which files are in scope, which tests must pass, and any other completion criteria. Booley creates an isolated worktree, where the Developer Agent runs any Booley Flows and Specialist reviews required by the ticket's acceptance criteria; the Harness tracks completion and hands you a review-ready result.

See FEATURES.md for the full list of capabilities.

Installation

Booley supports Windows and Linux (Ubuntu 24.04 tested); macOS is not supported. You need:

• Python 3.11+
• Docker
• VS Code with the Dev Containers extension
• Credentials for Claude (the default) or Codex
• Roughly 6 GB of Docker storage for the standard sandbox, proxy, and reaper images, plus additional disk space for project build artifacts

Install and verify the CLI on the host:

pipx install booley-rtl        # or: pip install booley-rtl
booley --version

pipx is recommended because it avoids system-Python conflicts. Windows users should run the CLI natively, not inside WSL. See Troubleshooting for first-run, PATH, and Python-environment problems, then continue to Setup.

Quick Start

Three ways in, ordered by how much you want to invest:

1. Level 1: Watch. See an engineer drive Booley on a demo project, start to finish. Zero setup.
2. Level 2: Try the demo yourself. Clone the configured demo, create a Ticket with the bundled ticket-creation skill, and run your own change.
3. Level 3: Use it on your own project. Full integration on your own RTL.

Level 1: Watch

Four videos show an engineer driving Booley on a demo project end to end, so viewers can see the workflow before touching anything:

1. Design Optimization (12:43)
2. Finding and Fixing Bugs (9:40)
3. Feature Ticket Creation (10:36)
4. Ticket Results Review (11:21)

The project's author recorded all four videos, then replaced the original narration with text-to-speech to preserve anonymity for now.

Level 2: Try the demo yourself

The demo IP is picorv32, Claire Wolf's open-source RISC-V CPU core. It is a small, area-optimized design with a straightforward multi-cycle architecture. That makes the RTL easy to understand and keeps lint, simulation, and synthesis runs fast, while still exercising Booley on a real project rather than a toy example.

First, complete the installation above.

Then follow the demo repository's README to try it yourself. Start in Interactive Mode: ask the agent to explain the design, inspect a Target, and run a lint or simulation Flow while you guide it. Once that feels familiar, try Ticket Mode as the optional autonomous workflow by creating a Ticket against the live design. The repository intentionally contains no pre-made Tickets.

Level 3: Use it on your own project

Follow SETUP.md to integrate Booley with your own RTL project.

Supported EDA Tools

Current integrations:

• Simulate / elaborate — Verilator, Icarus Verilog; cocotb testbenches supported
• Lint — Verilator, Verible
• ASIC synthesis (PPA estimate, not tape-out) — logical Yosys or physical Yosys + OpenROAD
• Waveform debug — bwave (+ VaporView GUI in VS Code)
• FPGA implementation — AMD Vivado
• Coming soon — Synopsys VCS, Cadence Xcelium

For exact versions, provisioning, trace support, and platform constraints, see SUPPORTED-EDA-TOOLS.md. Support for additional commercial EDA tools is coming soon; see the roadmap.

Limitations

• Booley will not design hardware for you. You design the architecture and write the specs; Booley handles the grunt work. Force multiplier, not replacement.
• You need prior digital design experience. Even the most advanced LLM is useless without electronic engineering fundamentals; Booley assumes you can read RTL, judge a waveform, and know what a sane result looks like.
• Source languages are SystemVerilog and Verilog only. VHDL is not supported.
• Testbenches are simple and direct. Direct SystemVerilog and cocotb testbenches are supported; UVM is not.
• Only tested at the IP level. Complex IPs, like a RISC-V core or crypto accelerators, but never chip- or SoC-level integration. See Ports for what has actually been through it.
• Setup can take effort. The setup skills make integration as smooth as I could get it, but every build system is different; complex flows or heavy licensed EDA tools may still need project-specific work. It's a price you pay once, though. After that, every ticket and every session builds on it, and development speeds up significantly.
• The code quality is "hardware engineer writing software." The architecture is sound, but the Python could use polish. Contributions from actual software developers are very welcome.
• Work in progress. Expect occasional bugs and rough edges in the UI. I'm actively on it, and things keep getting better.

Documentation

• Features
• Architecture
• Setup
• Usage
• Supported EDA tools

Advanced documentation lives in docs/.

Contributing

Booley is still early, so the most useful contribution is trying it and reporting what works, what doesn't, and what you want next. Tell /booley-feedback in your agent chat; it gathers and redacts any needed evidence. Opinions need no reproduction, and nothing leaves your machine until you approve the exact text (feedback guide, configuration).

Code and documentation contributions are welcome; see CONTRIBUTING.md. Please keep feedback technical and specific; broader debates about AI's effects on society or employment are outside the project's scope.

For suspected vulnerabilities, follow the private reporting process in SECURITY.md instead of opening a public issue.

Acknowledgments

Booley stands on a lot of other people's work. Thank you to:

• The authors of Edalize and FuseSoC, and especially their lead maintainer, Olof Kindgren, for the framework that makes Booley's whole idea of a simple, unified CLI-over-EDA interface possible.
• The author of vcdvcd, Ciro Santilli, for the VCD-parsing work that seeded the bwave idea.
• The author of wavepeek, another neat waveform-to-CLI EDA tool, for the clean top-level CLI interface that inspired bwave's top-level CLI (the internals started well before wavepeek and are quite different).
• The author of VaporView, Lloyd Ramseyer, for the excellent VS Code waveform viewer that bwave gui drives for scoped waveform inspection right in the IDE.
• The authors of Yosys, Verilator, Icarus Verilog, Verible, and sv2v, for the excellent open-source EDA tools that make Booley possible at all.
• Matt Pocock, for his great agentic software engineering techniques, which shaped how Booley's agents are built and driven.

License

Apache 2.0. See LICENSE for details.