AI & Agents
AIPOCH
Source: aipoch/open-science · ★ 1723 · TypeScript
Last updated 2026-08-06 · benchmark measured 2026-11-06 — deterministic & reproducible
AIPOCH builds an open-source AI workbench for reproducible medical research.
AIPOCH at a glance
AIPOCH's Open-Science is an open-source, local-first AI research workbench that lets medical and scientific researchers run AI agents to plan, execute, and document reproducible research tasks such as meta-analysis, protocol design, and cohort matching.
Good for
- Running reproducible meta-analyses with a full record of the steps and code used
- Designing study protocols, methods, and endpoints with agent assistance
- Searching, organizing, and synthesizing scientific literature with citation management
- Running Python and R data analysis workflows with traceable, versioned outputs
Pricing
Open-source under the Apache-2.0 license; free to download (Windows, macOS, Linux) and run locally. No separate price listed.
Questions people ask
Who is AIPOCH Open-Science built for?
It's aimed at medical researchers, scientists, clinical research teams, evidence synthesis specialists, and protocol designers.
Does Open-Science work with any AI model?
Yes, it is model-agnostic and supports multiple providers including GPT, Claude, Grok, DeepSeek, Qwen, GLM, Kimi, MiniMax, and StepFun, plus custom gateways.
Does my data stay on my own computer?
Yes, it is local-first by default, keeping project state on your machine and letting you control file, command, network, connector, and compute access through permissions.
Can the AI agent run code and analyses, not just suggest it?
Yes, agents can run Python, R, and shell commands directly, along with literature search and scientific data connectors, within a persistent workspace.
How does it keep research reproducible and auditable?
Every agent action is logged and approval-gated, and reports, tables, figures, and notebooks are kept as immutable versions linked to their inputs, code, execution history, and environment details; sessions can also be exported as a portable .science package for others to inspect.
Written by Legit.Show from aipoch.com on 2026-10-28. It does not change the score.
Are you the maker of AIPOCH? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/gh-aipoch-open-science/2026-11-06. That address never changes; this page moves with every re-measure.
Legit.Show scored AIPOCH 87/100 on 2026-11-06, measured across all 7 frames from its public surface. legit.show/s/gh-aipoch-open-science/2026-11-06
Is AIPOCH production-ready?
Legit.Show scores AIPOCH 87 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on AIPOCH (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 97/100
- Accessibility — 96/100
- Security — 25/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 100/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 89/100
- Discoverability — 100/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 493 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.
Who built it
product account @aipoch_ai
Who it's for
Medical researchers · Scientists · Clinical research teams · Evidence synthesis specialists · Protocol designers
Sources and updates
- Description
- Taken from aipoch.com's own website on 2026-08-06.
- Operator
- AIPOCH PTE. LTD., as named in aipoch.com's terms, privacy page or footer.
- Code
- github.com/aipoch/open-science.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-11-06.
Put together from public information, without AIPOCH's involvement. If anything here is wrong, tell us and a person will check it.
Visit AIPOCH → · Alternatives to AIPOCH → · How this was measured →
