AICTL vs improv.sh

AICTL and improv.sh 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.

AICTL

Each 'orbit' is one task: the harness selects it from a dependency-ordered backlog, runs the agent, then requires passing tests, lint, and type checks before closing the loop — no proof, no progress. Every run produces structured JSON artifacts (agent output, rubric scoring, a human-readable progress log) that you can inspect or replay without re-running the agent. The deterministic replay demo runs without an API key, so you can see the full cycle before wiring in a real model. Orbit is intentionally small — no hosted infrastructure, no GUI — which keeps it auditable and keeps you in control, but also means everything outside the core loop is your problem to build.

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.

Attribute	AICTL	improv.sh
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	Linux, macOS, Windows (Python)	VS Code, Cursor, Claude Code, terminal, Chrome
Pros	Validation gates (tests, lint, type checks) block task completion until the agent proves its work, so you stop merging diffs that pass a visual review but break the build. Dependency-ordered backlog selection keeps each run scoped to one task at a time, which means agents cannot skip prerequisites and produce output that assumes work that was never done. All four run artifacts are inspectable JSON and Markdown, so a post-mortem on a failed agent run takes minutes instead of reconstructing what happened from logs. Agent-neutral adapter contract lets you run the same task against different coding agents and compare structured evaluation scores — replacing 'it felt better' with actual rubric data. Deterministic replay runs without an API key, so you can validate the full harness loop in a new environment before spending any API budget.	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.
Cons	There is no REST API, hosted runtime, or scheduler: every orbit runs locally from the command line. Teams that need to trigger runs from a CI pipeline or across multiple machines have to wire that infrastructure themselves before Orbit is production-useful. The harness is intentionally minimal — no web UI, no notification system, no multi-repo coordination. When a team needs to manage more than a handful of concurrent agent tasks or wants a dashboard for non-engineering stakeholders, Orbit's output artifacts are not enough and teams move to a fuller platform rather than extending the harness. Adapter support depends on community contributions; if your agent does not already have an adapter and does not speak JSON on the CLI, you write the adapter yourself before the first orbit runs — there is no plug-and-play path for proprietary or GUI-only tools.	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.

Bottom line

AICTL and improv.sh 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 AICTL and improv.sh?

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

Is AICTL better than improv.sh?

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.