improv.sh vs Memex

improv.sh and Memex 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.

Memex

Orbit runs as a local harness that pulls one dependency-ordered task at a time, hands it to whichever coding agent you configure, then runs your tests, lint, and type checks before recording the result. Every run writes structured JSON artifacts — what the agent returned, how the output scored against a rubric, and a human-readable recommendation to accept, iterate, or stop. The audit trail is durable and replayable without an API key, which makes it usable in air-gapped environments. The tooling is intentionally minimal, so teams building on top of it will write their own adapter glue for agents that do not speak the expected JSON contract. Orbit does not manage the agent itself — it manages what the agent must prove.

Attribute	improv.sh	Memex
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, macOS, Python 3.7+
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.	Validation gates block task completion until tests, lint, and type checks pass, which means you stop shipping agent output that looks correct but breaks the build. Durable, structured artifacts written after every run — including rubric scoring and a human-readable progress log — so you have an audit trail when a stakeholder asks what the agent actually did last Tuesday. Deterministic replay with no API key required, so you can rerun any recorded orbit in a local or air-gapped environment without incurring model costs or network dependencies. Agent-neutral adapter contract, so swapping Claude for Codex behind the same task backlog produces comparable JSON artifacts instead of anecdotal impressions about which agent performed better. Dependency-aware backlog sequencing, which means the harness advances tasks in the order your project actually requires rather than letting an agent jump to a task whose prerequisites are still failing.
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.	Agents that do not return structured JSON output require a custom adapter before Orbit can score or validate them — that wrapper is yours to write and maintain, and the docs describe it as a contribution target rather than a solved problem. There is no hosted service, no web UI, and no managed execution layer; teams that need cloud-hosted runs, a visual dashboard, or multi-user access to the artifact store will build all of that infrastructure themselves or switch to a commercial agent orchestration platform that ships those layers. The harness is intentionally small, which means complex branching logic — tasks that conditionally fan out based on what a prior agent returned — is outside what Orbit models; teams with multi-path workflows end up scripting the branching outside Orbit and using the harness only for the leaf-level validation step.

Bottom line

improv.sh and Memex 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 Memex?

improv.sh is Free and open source, while Memex 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 Memex?

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.