Bothread vs improv.sh

Bothread 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.

Bothread

Bothread runs locally on your machine and coordinates MCP-compatible agents — Claude Code, Cursor, Gemini CLI, Codex, and others — on a single codebase through a shared room where agents claim files before editing them. You watch the live thread of agent activity and can pause, redirect, mute, or remove any agent mid-task. An optional approval gate lets you sign off before any action flagged as risky proceeds. The coordination layer calls no models itself and requires no API keys — it only manages the agents you are already running. The ceiling appears when your project requires agent tooling that does not speak MCP: any agent outside that protocol sits outside Bothread's coordination entirely.

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	Bothread	improv.sh
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	Local machine (127.0.0.1)	VS Code, Cursor, Claude Code, terminal, Chrome
Pros	File-claiming before any edit happens, so two agents cannot overwrite each other's work on the same file — the class of silent conflict that makes multi-agent setups unreliable on a shared codebase is eliminated by design. Optional approval gate for risky actions, which means you stay in the loop on consequential changes without having to watch every line the agents produce. No API keys and no cloud calls — Bothread coordinates agents you already run, so adding it does not change your cost structure or introduce a new data-transmission surface. Fully self-hosted on 127.0.0.1 with MIT source available, so teams with strict data-residency requirements can audit the coordination layer and verify nothing leaves the machine. Live thread visibility with per-agent pause, redirect, mute, and remove controls, which means you can intervene on one agent mid-task without stopping the rest of the room.	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	Any agent that does not speak MCP cannot join a Bothread room — it operates outside the file-claiming and conflict-prevention system entirely. Teams whose preferred agent lacks MCP support face a hard choice: swap the agent for an MCP-compatible alternative or accept that coordination is incomplete and one agent can still overwrite another's work. Bothread has no API surface of its own, so there is no programmatic way to integrate the coordination layer into a CI pipeline, a deployment script, or any automated workflow that sits outside the agents themselves. Teams that want coordination events surfaced in external tooling have no supported path to do that. The tool coordinates agents but does not task them — it has no built-in mechanism for splitting a feature into subtasks and routing each to the right agent automatically. Teams that need that kind of work decomposition will reach for a separate orchestration layer, at which point they are maintaining two systems.	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

Bothread 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 Bothread and improv.sh?

Bothread 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 Bothread 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.