open-codex-computer-use is a skill AI agent for Run AI agents locally to execute code tasks, improving development speed and protecting code privacy. Pricing: Free. As of 2026-11-05, KanonAgent records 10 upvotes. First indexed by KanonAgent on 2026-07-08.
An open-source alternative to GitHub Copilot's computer use, enabling AI agents to run code tasks locally for improved efficiency and data privacy.
10 upvotes
Tracked by Kanon since Jul 8, 2026
Status basis: npm_downloads_7d momentum fell to -2264 per 3d from 1685 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to -2264 per 3d from 1685 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -2712 per 3d from 16515 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -589 per 3d from 2313 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 1685 in the last 3d vs 39 in the 3d before (ratio 43.2x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 1685 in the last 3d vs 39 in the 3d before (ratio 43.2x, threshold 1.5x)
- Anomaly daily change 12118.0 is 10.3 standard deviations from this entity's own prior mean (-11.0±1178.3, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change -4026.3 is -3.9 standard deviations from this entity's own prior mean (59.5±1060.7, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change -4026.3 is -3.9 standard deviations from this entity's own prior mean (59.5±1060.7, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -542 per 3d from 1419 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 1419 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -5055 per 3d from 1682 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -5055 per 3d from 2019 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 2572 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 1682 per 3d from 5556 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 2019 per 3d from 10520 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 2572 per 3d from 9967 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 890 per 3d from 9967 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 10520 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 9967 in the last 3d vs 1283 in the 3d before (ratio 7.8x, threshold 1.5x)
- Anomaly daily change 2333.0 is 3.7 standard deviations from this entity's own prior mean (261.3±561.9, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 5301 in the last 3d vs 1019 in the 3d before (ratio 5.2x, threshold 1.5x)
- Anomaly daily change 2898.0 is 5.8 standard deviations from this entity's own prior mean (209.6±462.2, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 1609 (<= 40% of the prior window)
- Anomaly daily change 1283.0 is 5.9 standard deviations from this entity's own prior mean (51.4±209.6, baseline excludes this point) — unusual, not necessarily adoption
🔎 Known / Unknown
12 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 1 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | mcp | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · skill
Job to be doneRun AI agents locally to execute code tasks, improving development speed and protecting code privacy.
AutonomyL2 · tool-calling(evidence: "run Computer Use on macOS, Linux, and Windows…")
Who it is forDevelopers
Prerequisitesopen source · self-hostable
Integrationsmcp
PricingFree
Traction · why it is risingGaining attention for offering a self-hosted, privacy-focused alternative to cloud-based AI coding tools.
Why it matters
Its focus on local execution and open-source transparency addresses growing developer concerns about data security and tool dependency.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“npm i -g open-computer-use”— readme
“run Computer Use on macOS, Linux, and Windows”— readme
“wrapped as `MCP`”— readme
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building open-codex-computer-use? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is open-codex-computer-use?
An open-source alternative to GitHub Copilot's computer use, enabling AI agents to run code tasks locally for improved efficiency and data privacy.
What does open-codex-computer-use do?
Run AI agents locally to execute code tasks, improving development speed and protecting code privacy.
Why does open-codex-computer-use matter?
Its focus on local execution and open-source transparency addresses growing developer concerns about data security and tool dependency.
How much does open-codex-computer-use cost?
Free
Is open-codex-computer-use free?
Yes — open-codex-computer-use has a free tier. Pricing as stated on its own page: Free
Is open-codex-computer-use open source?
Yes — open-codex-computer-use is open source.
Can I self-host open-codex-computer-use?
Yes — open-codex-computer-use can be self-hosted.
What does open-codex-computer-use integrate with?
mcp
How popular is open-codex-computer-use?
As tracked by KanonAgent: 10 upvotes (first indexed 2026-07-08).
What are the best open-codex-computer-use alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, archify, open-design, deer-flow, ruflo, career-ops.