improv.sh vs taste-ai

improv.sh and taste-ai 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.

taste-ai

The tool reads your git history and prior session logs, extracts recurring coding patterns, and packs everything into a condensed context file — the vendor states a reduction from 56K tokens to roughly 1.9K tokens, with a caveat that results vary by project size and history depth. You run one command in your project directory, and the output is ready to feed to whichever agent you use next. There is no API, no cloud dependency, and no configuration file to maintain. The ceiling appears on projects with thin or no git history: if the repo is new or commits are sparse, the pattern-learning stage has precious little to work from. Teams with that constraint manually supply coding guidelines instead of relying on automatic extraction.

Attribute	improv.sh	taste-ai
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	CLI (cross-platform via bash/git)
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.	Compresses session history from tens of thousands of tokens down to under two thousand, so you stop hitting context limits mid-session and agents carry forward what they learned about your codebase rather than starting cold. Automatically extracts coding style from git history, which means you do not maintain a separate style-guide document that drifts out of sync with how your codebase actually evolves. Zero-config design with a one-line install, so there is no YAML to tune before the tool is useful — you run it and the output is ready to pass to an agent. Runs entirely locally with no API calls or cloud dependency, so session histories and proprietary code patterns never leave the machine — relevant for teams working under data-handling constraints. MIT-licensed and self-hosted, so you own the full pipeline and there is no vendor decision to remove a feature or change pricing that breaks your workflow.
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.	On a greenfield project — or any repo where commits are sparse or generic — the pattern-extraction step returns little signal, and the compressed context ends up no more useful than a hand-written system prompt. Teams with new repos write explicit coding guidelines manually, bypassing the tool's primary feature. There is no API surface, so taste cannot be wired into a CI/CD pipeline or triggered automatically when a session ends; someone has to run the command by hand each time, which becomes friction on teams running many parallel agent sessions. The repo shows 7 stars and 0 pull requests at the time of curation, indicating a very early-stage project with no visible community contributions — teams betting this on production context management have no community-maintained integrations or bug fixes to fall back on, and a project with this footprint carries real abandonment risk. Teams that need a supported, actively maintained context management layer evaluate alternatives with larger ecosystems rather than build process dependencies on a single-maintainer utility.

Bottom line

improv.sh and taste-ai 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 taste-ai?

improv.sh is Free and open source, while taste-ai 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 taste-ai?

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.