Mngr is a CLI tool for programmatically spinning up coding agents at any scale. It lets you compose workflows—fix all my tests, open PRs for every issue, validate every use case—and run them repeatedly. Run 1. Run 100s. See all your agents, and if they're blocked on you. Connect to any agent mid-task to ask a question or debug it. Agents start in under 2 seconds and shut down when idle. The same commands work with any agent harness, running locally, on Modal, or in Docker. Free and open-source.

Twitter's algorithm is optimized for attention, not for you. We want to change that. Bouncer is a Chrome extension and iPhone app that filters out what you don't want to see: a phrase, a topic, a tone. How it works: A small language model is used to understand context from keywords. Filter out "AI doomerism" or "crypto" or even something as broad as "arrogance." And because Twitter's algorithm learns from what you look at, or don't, using Bouncer starts to heal the feed itself.

Getting your agent authenticated with third-party services shouldn't require a custom connector for each one. Add Latchkey once and agents prepend latchkey to standard curl calls. Credentials are detected and injected automatically. They're stored encrypted on your machine, and never show up in logs or chat transcripts. 25+ services supported out of the box. Register any HTTP API at runtime. Works with Claude Code, OpenCode, Codex, and more. Open source software by Imbue.

Keystone self-configures a working devcontainer for any git repo, all on its own. Give it a repo. Get back a Dockerfile, devcontainer.json, and a passing test runner. It runs a coding agent inside a sandboxed Modal environment so your machine is never touched. It’s open-source, works with Claude Code and Codex, and the dev containers it produces work in VS Code and GitHub Codespaces. pip install imbue-keystone

Vet is a fast and local code review tool open-sourced by the Imbue team. It’s concise where others are verbose, and it catches more relevant issues. Vet verifies your coding agent's work by considering your conversation history to ensure the agent's actions align with your requests. It catches the silent failures: features half-implemented, tests claimed but never run. It reviews full PRs too, like logic errors, unhandled edge cases, and deviations from stated goals.

We built Offload after watching an agent wait 10 mins for an integration run to finish. When you're running parallel AI coding agents, the test suite is where the loop stalls. Agents queue behind a test lock or race for local resources to return flaky results. Offload is an open-source Rust CLI your agents invoke directly. It spreads your test suite across 200+ isolated cloud sandboxes. One TOML config, no test rewrites. On our Playwright suite, it took a 12 mins run to 2, at $0.08 per run.

Imbue develops tools that help people think, create, and build. We believe technology should be loyal to the user and aligned with human goals.