improv.sh vs Jacquard

improv.sh and Jacquard are both cli coding agents tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

improv.sh

improv operates as a task harness: the @im call pulls repo context, detects your test commands, writes acceptance criteria, and packages shell validation steps into one spec the agent can implement on turn one. The loop infrastructure is the distinguishing piece — judges run your actual exit-code commands (npm test, typecheck, build), so done means your tests pass, not that the agent says it's done. The tool installs locally via curl with no external API keys required, and the Chrome extension brings the same engine into web-based chat interfaces. The 920-skill library and daily auto-research loop suggest the routing layer will keep growing — but the page offers no independent benchmarks to validate the token-savings figures cited.

Jacquard

Jacquard is a small programming language with a surface syntax (.jac files), an OCaml type-checker, a CPS interpreter, and a C-emitting AOT backend — the full stack for running, reviewing, and simulating model-written programs. Its core differentiator is language-level effect tracking: the runtime can surface what a program touches and what authority it claims before you let it run. The Warp tool lets you execute code against multiple simulated or real worlds, which means policy and risk scenarios become testable rather than theoretical. The project is Apache-2.0 licensed with free binaries and a self-hosted install path. This is a research project — the community is small, the ecosystem is thin, and production support does not exist.

Attribute	improv.sh	Jacquard
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	VS Code, Cursor, Claude Code, terminal, Chrome	Linux x86-64, macOS Intel, macOS Apple Silicon
Pros	Repo-aware spec compilation pulls your actual test commands and package scripts into the task before the agent starts, which means the agent implements against your real constraints instead of inventing them mid-run. Exit-code judges close the loop on real shell commands — npm test, typecheck, build — so you are not relying on the agent's self-assessment of whether it finished. Task memory persisted under .improv/tasks/ survives session boundaries, so an agent restarted mid-task picks up status and spec instead of starting the discovery cycle again. Local-first install with no external API keys required, which means the harness runs in air-gapped or locked-down environments where cloud tooling is blocked. Chrome extension and VS Code/Cursor Marketplace extension share the same local engine, so the spec compilation and judge loop work whether you are in the IDE or a browser-based chat interface — without switching tabs.	Language-level effect tracking lets reviewers inspect what authority a model-written program claims before it executes, which means you catch over-privileged code at review time rather than after it runs in production. Warp simulation runs the same program against multiple environments, so policy and risk edge cases become testable artifacts rather than thought experiments. Apache-2.0 license with self-hosted install path means no vendor dependency and no data leaves your infrastructure — critical when reviewing proprietary or sensitive model output. CPS interpreter and C-emitting AOT backend in the same toolchain, so you can prototype in interpreted mode and then compile without switching environments. Free and open-source with no paid tier gating any features, so the full capability set is available to a research team without a procurement process.
Cons	Task state is written to .improv/tasks/ on the local machine. Teams with more than one developer working the same codebase have no shared task state — there is no sync layer described on the page — so parallel agent runs on different machines produce divergent task records with no reconciliation path. The tool exposes no API surface, so teams that want to trigger improv from a CI pipeline or wrap it in a custom orchestration layer cannot. Teams hitting this wall move to harness frameworks that expose programmatic interfaces — at which point they are maintaining the prompt compilation logic themselves. The token-savings figures on the page (~613 tokens median) are vendor-reported with no independent reproduction methodology described. Teams making adoption decisions based on cost reduction should treat these numbers as illustrative until they run their own baseline comparison. Chrome extension installation requires either the Chrome Web Store or a manual sideload script — neither path is available in Firefox or Safari. Teams on non-Chromium browsers are limited to the terminal install, losing the browser chat integration entirely.	Jacquard is its own language with its own syntax — any team that wants to review Python, TypeScript, or Go output from a model gets nothing here. Teams with existing codebases in mainstream languages will hit this wall immediately and route around it by staying in their host language's static analysis ecosystem. The community is tiny: 73 stars and no open issues or pull requests at the time of scrape. When you hit a bug or an underdocumented behavior, there is no forum, no Stack Overflow tag, and no vendor support line — you read the source or file an issue into the void. The C-emitting AOT backend is described as a work in progress in the scrape ('cur' is where the description cuts off). Teams that need a stable compilation target for anything approaching production will find themselves blocked and move to a language with a mature compiler toolchain.

Bottom line

improv.sh and Jacquard are closely matched on pricing model, openness, and API availability — pick by feature set and platform support in the table above.

Frequently asked questions

What is the difference between improv.sh and Jacquard?

improv.sh is Free and open source, while Jacquard is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is improv.sh better than Jacquard?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.