synthetic-sciences/opensciencePublic

The open-source AI workbench for scientific research

AI summary: An open-source AI workbench that autonomously conducts end-to-end scientific research.

Stars
4.4K
+17 today
Forks
554
Watchers
19
Open issues
2
Open PRs
9
Contributors
~19
Commits
1.2K
Branches
10

TypeScriptApache-2.0Created Jul 3, 2026Last push todayLatest release v2.0.153+27 stars this week+231 this month

Quick answers

What is openscience?
An open-source AI workbench that autonomously conducts end-to-end scientific research.
What does openscience do?
OpenScience is an ambitious AI-driven platform designed to automate the scientific research process. Users provide a high-level goal, and the system autonomously reviews relevant literature, writes code to perform experiments, executes that code, and analyzes the results. It attempts to close the loop on research by summarizing its findings in a written format, effectively acting as an autonomous research assistant. The workbench integrates various tools for literature search, code execution, and data analysis into a cohesive workflow. It aims to accelerate scientific discovery by automating the mechanical aspects of research.
Who is openscience for?
Researchers, data scientists, and academics looking to automate parts of their workflow. AI developers interested in building autonomous agents for complex, multi-step problem solving.
How do I get started with openscience?
Follow the installation instructions in the README or visit openscience.sh/docs for a quickstart guide.
How popular is openscience on GitHub?
synthetic-sciences/openscience has 4,404 stars and 554 forks on GitHub, and gained 27 stars in the last 7 days.
What license does openscience use?
synthetic-sciences/openscience is released under the Apache-2.0 license.

Star history

since Jul 29, 2026
02K4KJul 2026Sep 2026Oct 2026Nov 2026
4.4K stars as of Nov 20, 2026. Measured daily since Jul 29, 2026; GitHub no longer exposes earlier star timestamps.

Update history

3 recorded
  • Nov 1, 2026New release v2.0.153 (previously v2.0.152).
  • Oct 21, 2026New release v2.0.152 (previously v2.0.151).
  • Oct 9, 2026New release v2.0.151 (previously v2.0.139).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 0 commits2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 0 commits2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 0 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 0 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 0 commits2026-04-29: 0 commits2026-04-30: 0 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 0 commits2026-05-12: 0 commits2026-05-13: 0 commits2026-05-14: 0 commits2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 0 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 0 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 0 commits2026-06-26: 0 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 0 commits2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 0 commits2026-07-04: 6 commits2026-07-05: 33 commits2026-07-06: 99 commits2026-07-07: 29 commits2026-07-08: 32 commits2026-07-09: 8 commits2026-07-10: 7 commits2026-07-11: 12 commits2026-07-12: 30 commits2026-07-13: 5 commits2026-07-14: 15 commits2026-07-15: 2 commits2026-07-16: 0 commits2026-07-17: 0 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 0 commits2026-07-21: 0 commits2026-07-22: 1 commit2026-07-23: 0 commits2026-07-24: 0 commits2026-07-25: 9 commits2026-07-26: 10 commits2026-07-27: 17 commits2026-07-28: 0 commits2026-07-29: 44 commits2026-07-30: 0 commits2026-07-31: 1 commit2026-08-01: 0 commits2026-08-02: 3 commits2026-08-03: 1 commit2026-08-04: 2 commits2026-08-05: 0 commits2026-08-06: 13 commits2026-08-07: 10 commits2026-08-08: 4 commits2026-08-09: 3 commits2026-08-10: 0 commits2026-08-11: 0 commits2026-08-12: 0 commits2026-08-13: 0 commits2026-08-14: 5 commits2026-08-15: 6 commits2026-08-16: 0 commits2026-08-17: 0 commits2026-08-18: 3 commits2026-08-19: 3 commits2026-08-20: 19 commits2026-08-21: 7 commits2026-08-22: 4 commits2026-08-23: 3 commits2026-08-24: 18 commits2026-08-25: 12 commits2026-08-26: 20 commits2026-08-27: 43 commits2026-08-28: 23 commits2026-08-29: 27 commits2026-08-30: 28 commits2026-08-31: 6 commits2026-09-01: 3 commits2026-09-02: 0 commits2026-09-03: 6 commits2026-09-04: 27 commits2026-09-05: 16 commits2026-09-06: 8 commits2026-09-07: 14 commits2026-09-08: 15 commits2026-09-09: 9 commits2026-09-10: 22 commits2026-09-11: 15 commits2026-09-12: 9 commits2026-09-13: 6 commits2026-09-14: 6 commits2026-09-15: 20 commits2026-09-16: 28 commits2026-09-17: 40 commits2026-09-18: 23 commits2026-09-19: 13 commits2026-09-20: 45 commits2026-09-21: 2 commits2026-09-22: 3 commits2026-09-23: 3 commits2026-09-24: 29 commits2026-09-25: 6 commits2026-09-26: 16 commits2026-09-27: 17 commits2026-09-28: 13 commits2026-09-29: 40 commits2026-09-30: 2 commits2026-10-01: 1 commit2026-10-02: 27 commits2026-10-03: 0 commits2026-10-04: 3 commits2026-10-05: 3 commits2026-10-06: 1 commit2026-10-07: 0 commits2026-10-08: 2 commits2026-10-09: 5 commits2026-10-10: 2 commits2026-10-11: 0 commits2026-10-12: 1 commit2026-10-13: 4 commits2026-10-14: 0 commits2026-10-15: 0 commits2026-10-16: 0 commits2026-10-17: 0 commits2026-10-18: 17 commits2026-10-19: 0 commits2026-10-20: 2 commits2026-10-21: 0 commits2026-10-22: 0 commits2026-10-23: 0 commits2026-10-24: 0 commits2026-10-25: 0 commits2026-10-26: 1 commit2026-10-27: 0 commits2026-10-28: 1 commit2026-10-29: 0 commits2026-10-30: 10 commits2026-10-31: 0 commits2026-11-01: 0 commits2026-11-02: 0 commits2026-11-03: 0 commits2026-11-04: 0 commits2026-11-05: 0 commits2026-11-06: 0 commits2026-11-07: 0 commits2026-11-08: 0 commits2026-11-09: 0 commits2026-11-10: 0 commits2026-11-11: 3 commits2026-11-12: 2 commits2026-11-13: 0 commits2026-11-14: 0 commits
1,164 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Very active

    1,164 commits in 52 weeks

  • Well documented

    High community health score

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

What openscience does

OpenScience is an ambitious AI-driven platform designed to automate the scientific research process. Users provide a high-level goal, and the system autonomously reviews relevant literature, writes code to perform experiments, executes that code, and analyzes the results. It attempts to close the loop on research by summarizing its findings in a written format, effectively acting as an autonomous research assistant. The workbench integrates various tools for literature search, code execution, and data analysis into a cohesive workflow. It aims to accelerate scientific discovery by automating the mechanical aspects of research.

Researchers, data scientists, and academics looking to automate parts of their workflow. AI developers interested in building autonomous agents for complex, multi-step problem solving.

  • Autonomous research loop: Capable of planning, executing, and summarizing research tasks based on a simple goal.
  • Literature review integration: Automatically searches and reads relevant scientific literature to inform its work.
  • Code generation and execution: Writes, debugs, and runs code to perform required experiments or data analysis.
  • Automated write-ups: Synthesizes experimental results and literature into cohesive reports or summaries.
  • Open-source architecture: Provides a transparent, modifiable workbench for the scientific community.

Where teams use it

Exploratory data analysis

Tasking the agent to find a dataset, analyze it for specific patterns, and write a summary report.

Literature synthesis

Asking the system to review recent papers on a topic and compile a comprehensive summary of the current state of the art.

Automated experimentation

Running computational experiments or simulations across various parameters without manual intervention.

Research assistance

Delegating the initial, time-consuming stages of a research project to an AI agent to accelerate discovery.

Getting started: Follow the installation instructions in the README or visit openscience.sh/docs for a quickstart guide.

README

main branch
OpenScience

The open-source AI workbench for scientific research.

Give it a goal. It reads the literature, writes and runs the code, runs the experiments, and writes up what it found, with every step on the record.


CI npm release license

Download · Quickstart · Documentation · Changelog · Contributing


An OpenScience session comparing EGFR inhibitor potency: the trace shows the search, the written files, the analysis run and the answer with a results table

What it is

OpenScience is a research agent with a workbench around it. You describe the task in plain language; it plans, gathers evidence, runs code and experiments, and hands back results you can check. It runs as a desktop app, a browser workspace, or a terminal command, on your machine, against your files.

It is built for the parts of research that are real work but not the idea: pulling and cleaning data, reproducing a claim, sweeping a parameter, drafting the methods section, checking a reference. You keep the idea and the judgment.

  • Every step is visible. A turn reads as what happened: what it thought, what it searched, what it ran, what it wrote, then the answer. Nothing runs that you cannot see afterwards.
  • Real tools, real files. Shell, Python and R kernels, notebooks, a file system with explicit read and write grants, remote compute when a laptop is not enough.
  • Scientific reach. Hundreds of bundled skills across biology, chemistry, physics, ML and data engineering, plus connectors to databases such as ChEMBL, UniProt, PubMed and arXiv.
  • Delegation when it helps. The lead agent can hand bounded work to workers, in parallel, and keeps the synthesis and the final say.
  • Your model, your terms. Bring your own API keys, sign in to a supported provider, run a local model, or use Ace, the managed pay-as-you-go option.

Install

Desktop app. Download for macOS, Windows or Linux. It updates itself.

Command line and browser workspace.

npm install -g @synsci/openscience
openscience

Or run it without installing:

npx synsci

Or with the standalone installer on macOS and Linux:

curl -fsSL https://openscience.sh/install | bash

Then open Customize → Models and connect a provider, or from the terminal:

openscience keys add        # your own API key
openscience local add       # Ollama, LM Studio, or another local endpoint

The installation guide covers platform details, updates and uninstalling.

First task

Open a project folder and describe the work:

openscience ~/research/my-project
Inspect data/samples.csv for missing values and inconsistent labels.
Keep the original data unchanged. Save a quality report and a plot
in results/, with the code needed to reproduce them.

Start with /plan when you want to agree on the method first. For a single turn from a script or a pipeline:

openscience run "Review the analysis plan in this project"
openscience run --continue "Suggest checks for the assumptions you identified"

Review sources, assumptions, code and outputs before relying on a scientific conclusion. The agent shows you what it did so that you can.

What you can do

Task What happens
Review literature Search scientific sources, compare findings, save cited evidence.
Analyze data Inspect inputs, write and run analysis code, produce figures and reports.
Reproduce experiments Agree on a claim, prerequisites and budget, then compare measured results.
Run compute Local kernels for everyday work; Modal, SSH hosts, or Slurm and PBS clusters for GPUs and long jobs, approved before they run.
Reuse procedures Browse the bundled skills or add a workflow specific to your lab.
Extend it MCP servers, custom agents and commands, plugins, or the TypeScript SDK.

A skill describes a procedure; it does not mean every tool or service it references is installed. Check availability in Customize before a substantial task.

NVIDIA BioNeMo

OpenScience ships ten bring-your-own-key adapters for NVIDIA BioNeMo NIM endpoints: Boltz-2, DiffDock, Evo 2, GenMol, MolMIM, MSA Search, OpenFold2, OpenFold3, ProteinMPNN and RFdiffusion. Each has a strict request schema, one approval per dispatch, and hashed artifacts written into the session; they are marked experimental and need your own NVIDIA API key under NVIDIA's service terms. The protein-binder-design skill is adapted from the NVIDIA BioNeMo Agent Toolkit (CC-BY-4.0 skills, Apache-2.0 code), pinned at commit 0e67a61. See Scientific tools and Service credentials.

How it works

your request
  → Research agent plans, then works step by step
      → tools: shell, Python/R kernels, files, search, connectors, compute
      → workers for bounded parallel tasks (explore, general, and five domain specialists)
  → answer, with the trace and the files it produced
  • Permissions. Choose how much to ask: always, only for risky actions, or full access. Network commands ask once per destination host. Files outside the project are read or written only with an explicit grant.
  • Working folder. A conversation works in the project's connected folder; caches and throwaway output stay in a per-session scratch space.
  • Publishing stays with you. git push, releases and uploads run from the lead session with this machine's own GitHub and Hugging Face logins; no token is ever asked for in chat.

The capability map, Explore tools and the skills directory list what is available and how to set it up.

Benchmarks

Benchmark OpenScience
Terminal-Bench Science (70 tasks) 53/70 (75.7)
BiomniBench-DA (public 50) 82.2
Terminal-Bench 4.0, science subset (14 tasks) 0.714 (10/14)

GPT-6 Astra and GPT-6 Sol on Harbor, with each benchmark's native environments, verifiers and judge. The results, with the trace of every counted trial, are in benchmarks-openscience.

Model access

Option Setup Cost
Your provider An API key or a supported sign-in. Your provider's billing.
Local model Ollama, LM Studio or any compatible endpoint. Your hardware.
Ace Sign in, choose a workspace, fund its Wallet. Pay as you go at the Wallet rate shown for each model.

Ace has no subscription. Direct provider routes add no fee; models served through OpenRouter include its funding fee (5.5% by default), already counted in the displayed rate. The card processing fee is shown at checkout.

First-run setup asks you to sign in to an OpenScience account; headless openscience run does not. Model usage through your own keys or a local model is never charged to an Ace Wallet. Details are in Models, Local models and Pricing.

Documentation

Topic Guides
First use Quickstart, Workspace, Workflow cookbook
Research Literature reviews, Data analysis, Reproduction, Writing
Capabilities Skills, Databases, Connectors
Control Permissions, Files, Project instructions, Configuration
Automate CLI reference, JSON output, SDK and editors
Help Troubleshooting, FAQ

The documentation is also available as plain text for agents: llms.txt and llms-full.txt.

Repository

backend/cli          The openscience CLI and local server: sessions, tools, providers, skills
frontend/workspace   The browser workspace (SolidJS), embedded into the CLI at build time
frontend/ui          Shared components, themes and icons
frontend/desktop     The Electron shell and its signed self-updater
frontend/docs        The documentation site
tooling/sdk          The TypeScript SDK, generated from the server's OpenAPI contract
tooling/plugin       The plugin runtime
docs/notes           Engineering notes: verification, releases, how to add a skill, tool or connector
bun run setup        # verify Bun, install, embed the workspace UI
bun dev              # run from source
bun run check        # format, typecheck and every unit suite

ARCHITECTURE.md explains how the pieces fit. CONTRIBUTING.md has the development loops, the checks that gate a pull request, and how to add a skill, connector, tool or plugin. AGENTS.md holds the conventions the code follows.

Releases

Stable releases are cut from main by the publish workflow after a full rehearsal at the same commit: packaged end-to-end tests, operating-system smokes and scientific capability canaries on every native platform. GitHub Releases carries the desktop installers, CLI archives and checksums; the changelog records what changed for users.

The desktop app updates itself. For the CLI, run openscience upgrade, or npm install -g @synsci/openscience@latest for an npm installation.

Community and support

  • Bugs and feature requests: GitHub Issues. Use the templates; a good report has a reproduction.
  • Security: SECURITY.md. Please report vulnerabilities privately.
  • Conduct: CODE_OF_CONDUCT.md.
  • Billing and account questions: use the account support channel rather than a public issue.

Acknowledgements

OpenScience is inspired by OpenCode by Anomaly and shares its commitment to excellent open-source agents. We want to bring strong, open-source scientific agents to everyone.

Most of the bundled skills come from open collections written by other people:

backend/cli/skills/ATTRIBUTION.md lists every derived skill with its upstream path and license, and each skill's frontmatter names its original author. NOTICE carries the license texts.

License

Apache License 2.0. See LICENSE and NOTICE.

OpenScience is an independent project. It is not affiliated with, endorsed by, or sponsored by any model provider. Provider and model names are used only to describe compatibility.

View on GitHub

Recent activity

commits and pull requests

Recent open issues

view all

Releases and announcements

150 total
  1. v2.0.153v2.0.153Oct 30, 20261.7K downloads

    ## Usage and sessions - Check settled Ace Wallet receipts for a task and its workers from the Context panel. Unchecked, pending, unavailable, and incomplete results stay explicit. - Keep provider-reported costs, catalog estimates, imported charges and credits, and historical accounting separate in Usage, CSV exports, and `openscience stats`. Import normalized provider billing JSON locally and match records by exact request IDs. - Simplify the Context panel and preserve estimated system-instruction and tool-definition counts after a page reload. Older calls without saved counts remain marked as not reported. - Store sessions and delegated Task replay records in SQLite, preserving existing IDs and original JSON migration backups. Recover later legacy records without reviving deleted backups. - Expand local and server logging-health checks to cover failed, cancelled, and retried model calls, delivery acknowledgements, and incomplete settlement evidence. - Edit autoresearch study questions and hypotheses, and retain linked compute-job provenance in run details. ## Reliability fixes - Discard local credential-sync retries and responses from earlier sign-ins after logout, account chan

  2. v2.0.152v2.0.152Oct 18, 20262.4K downloads

    ## Core - Find Git Bash in UCRT64 installations (#1003) - Bound decoded streams and cancel incomplete requests (#998) - Add opt-in anonymous Parallel Search preset (#1000) - Add approved Argon and document subscription routes (#999) - Cancel rejected image download streams (#993) (xiaofeilovecoding) - Bump web-tree-sitter from 0.25.10 to 0.27.1 (#990) - Drop the claude-code beta header from Anthropic requests (#996) (Jinho Kim) - Bump vscode-languageserver-types from 3.18.3 to 3.18.4 (#991) - Audit model calls across routes (#973) - Link each model call to its Ace charge (#958) - Bump @zip.js/zip.js from 2.7.62 to 2.23.0 (#969) - Point plotly and neuropixels links at references/ (#961) - Keep every token when rebuilding inverted-index abstracts (#957) (Zhibo Zhang (Amur)) ## App - Update six development tools with explicit package globals (#997) - Bump the solid group with 4 updates (#987) - Bump igv from 3.8.4 to 3.8.9 (#970) ## Desktop - Bump electron from 44.0.0 to 44.5.1 (#971) ## Website - Bump postcss in /frontend/landing in the landing group (#986) - Drop the data and privacy FAQ entry (#978) - Give every docs page its own URL and prerendered HTML (#976) - Prerender each pag

  3. v2.0.151v2.0.151Oct 5, 20261.8K downloads

    ## More reliable research sessions - Keep GPT-6 Sol and GPT-6.1 Sol available through connected ChatGPT/Codex subscriptions, with supported reasoning controls and Fast mode for 6.1. GPT-6 Sol is removed from the Ace roster. - Stop unattended runs from inventing work after a greeting. - Preserve tool availability across retries, restore sessions containing malformed todo history, and keep pagination complete when sessions share a timestamp. - Prevent stale Codex sign-in timers from clearing newer attempts and keep provider web-search events consistent. ## Workspace and desktop - Recover the newest verified pending desktop update. - Preserve unsaved-file warnings when new edits arrive while a confirmation dialog is open. - Restore the live Modal job panel and retain balance-recovery guidance across gateway response formatting changes. - Preserve skill acronym casing and display escaped Markdown safely when sanitization is unavailable. ## Datasets and scientific helpers - Create Hugging Face datasets privately by default; use `--public` to publish a new dataset publicly. Upload failures now return a failing exit status. - Validate question-answering, completion, and union fields.

  4. v2.0.150v2.0.150Oct 2, 20261.1K downloads

    ## Models and provider setup - Add OpenAI GPT-6.1 Sol with supported reasoning controls and Fast mode. - Configure custom model Base URLs and OpenAI protocol selection in Settings. - Removing a provider key disconnects its saved connection while retaining endpoint and protocol preferences. - Improve research-search setup guidance and Chinese settings and connection messages. ## Terminals and Claude Code - Open new terminals in the selected working folder and load the user’s login shell and installed commands. - Give user-operated terminals normal local access while preserving the research agent’s sandbox. - Launch the installed Claude Code CLI from the Terminal panel with its existing login and session history. This is an interactive terminal session; the research-chat model remains independently configured. ## Remote workspaces and scientific connectors - Open a trusted remote runtime through an existing SSH tunnel in an isolated desktop window. Files, events, and terminals stay on the selected server. The tunnel must already be running; authenticated-runtime sign-in and automatic SSH management remain follow-up work. - Add keyless BioSimulators registry search and version-sp

  5. v2.0.149v2.0.149Oct 2, 2026279 downloads

    ## Windows signing - Sign the Windows desktop installer, application, bundled CLI, and native libraries with Microsoft Artifact Signing. - Verify trusted, timestamped signatures from Inkvell Inc. before publication. This patch includes the fixes and improvements from [v2.0.148](https://github.com/synthetic-sciences/openscience/releases/tag/v2.0.148). **Full changelog:** https://github.com/synthetic-sciences/openscience/compare/v2.0.148...v2.0.149 <!-- openscience-release-source:b500a2616aa6795b7149be70455adf10f7f32902 -->

Code frequency

additions and deletions
+915.4K-915.4KWeek of 2026-06-28: +915,385 linesWeek of 2026-06-28: -248 linesWeek of 2026-07-05: +51,349 linesWeek of 2026-07-05: -49,213 linesWeek of 2026-07-12: +7,063 linesWeek of 2026-07-12: -3,396 linesWeek of 2026-07-19: +1,495 linesWeek of 2026-07-19: -207 linesWeek of 2026-07-26: +202,744 linesWeek of 2026-07-26: -8,217 linesWeek of 2026-08-02: +123,200 linesWeek of 2026-08-02: -45,355 linesWeek of 2026-08-09: +125,100 linesWeek of 2026-08-09: -51,085 linesWeek of 2026-08-16: +37,192 linesWeek of 2026-08-16: -15,441 linesWeek of 2026-08-23: +145,396 linesWeek of 2026-08-23: -51,068 linesWeek of 2026-08-30: +66,018 linesWeek of 2026-08-30: -82,365 linesWeek of 2026-09-06: +62,461 linesWeek of 2026-09-06: -17,781 linesWeek of 2026-09-13: +372,807 linesWeek of 2026-09-13: -96,123 linesWeek of 2026-09-20: +28,744 linesWeek of 2026-09-20: -5,218 linesWeek of 2026-09-27: +15,624 linesWeek of 2026-09-27: -2,522 linesWeek of 2026-10-04: +3,176 linesWeek of 2026-10-04: -418 linesWeek of 2026-10-11: +678 linesWeek of 2026-10-11: -288 linesWeek of 2026-10-18: +12,725 linesWeek of 2026-10-18: -1,144 linesWeek of 2026-10-25: +6,911 linesWeek of 2026-10-25: -922 linesWeek of 2026-11-01: +0 linesWeek of 2026-11-01: -0 linesWeek of 2026-11-08: +11,151 linesWeek of 2026-11-08: -543 linesJun 28, 2026Nov 8, 2026
+2.2M lines added, -431.6K removed over the last year.

Commits per week

last 52 weeks
2200Week of 2025-11-16: 0 commitsWeek of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 0 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 0 commitsWeek of 2026-04-05: 0 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 0 commitsWeek of 2026-04-26: 0 commitsWeek of 2026-05-03: 0 commitsWeek of 2026-05-10: 0 commitsWeek of 2026-05-17: 0 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 0 commitsWeek of 2026-06-07: 0 commitsWeek of 2026-06-14: 0 commitsWeek of 2026-06-21: 0 commitsWeek of 2026-06-28: 6 commitsWeek of 2026-07-05: 220 commitsWeek of 2026-07-12: 52 commitsWeek of 2026-07-19: 10 commitsWeek of 2026-07-26: 72 commitsWeek of 2026-08-02: 33 commitsWeek of 2026-08-09: 14 commitsWeek of 2026-08-16: 36 commitsWeek of 2026-08-23: 146 commitsWeek of 2026-08-30: 86 commitsWeek of 2026-09-06: 92 commitsWeek of 2026-09-13: 136 commitsWeek of 2026-09-20: 104 commitsWeek of 2026-09-27: 100 commitsWeek of 2026-10-04: 16 commitsWeek of 2026-10-11: 5 commitsWeek of 2026-10-18: 19 commitsWeek of 2026-10-25: 12 commitsWeek of 2026-11-01: 0 commitsWeek of 2026-11-08: 5 commitsNov 16, 2025Nov 8, 2026
1.2K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 9 commitsSun 1:00 — 9 commitsSun 2:00 — 9 commitsSun 3:00 — 8 commitsSun 4:00 — 1 commitsSun 5:00 — 2 commitsSun 6:00 — 11 commitsSun 7:00 — 5 commitsSun 8:00 — 5 commitsSun 9:00 — 5 commitsSun 10:00 — 3 commitsSun 11:00 — 3 commitsSun 12:00 — 7 commitsSun 13:00 — 7 commitsSun 14:00 — 20 commitsSun 15:00 — 18 commitsSun 16:00 — 9 commitsSun 17:00 — 14 commitsSun 18:00 — 9 commitsSun 19:00 — 9 commitsSun 20:00 — 8 commitsSun 21:00 — 11 commitsSun 22:00 — 19 commitsSun 23:00 — 5 commitsMon 0:00 — 2 commitsMon 1:00 — 3 commitsMon 2:00 — 1 commitsMon 3:00 — 7 commitsMon 4:00 — 2 commitsMon 5:00 — 2 commitsMon 6:00 — 4 commitsMon 7:00 — 0 commitsMon 8:00 — 1 commitsMon 9:00 — 17 commitsMon 10:00 — 22 commitsMon 11:00 — 15 commitsMon 12:00 — 39 commitsMon 13:00 — 8 commitsMon 14:00 — 4 commitsMon 15:00 — 1 commitsMon 16:00 — 4 commitsMon 17:00 — 6 commitsMon 18:00 — 3 commitsMon 19:00 — 6 commitsMon 20:00 — 17 commitsMon 21:00 — 14 commitsMon 22:00 — 6 commitsMon 23:00 — 2 commitsTue 0:00 — 5 commitsTue 1:00 — 1 commitsTue 2:00 — 9 commitsTue 3:00 — 1 commitsTue 4:00 — 4 commitsTue 5:00 — 3 commitsTue 6:00 — 3 commitsTue 7:00 — 7 commitsTue 8:00 — 4 commitsTue 9:00 — 17 commitsTue 10:00 — 6 commitsTue 11:00 — 8 commitsTue 12:00 — 4 commitsTue 13:00 — 6 commitsTue 14:00 — 2 commitsTue 15:00 — 9 commitsTue 16:00 — 11 commitsTue 17:00 — 7 commitsTue 18:00 — 5 commitsTue 19:00 — 3 commitsTue 20:00 — 6 commitsTue 21:00 — 23 commitsTue 22:00 — 4 commitsTue 23:00 — 1 commitsWed 0:00 — 0 commitsWed 1:00 — 1 commitsWed 2:00 — 4 commitsWed 3:00 — 4 commitsWed 4:00 — 0 commitsWed 5:00 — 4 commitsWed 6:00 — 9 commitsWed 7:00 — 6 commitsWed 8:00 — 9 commitsWed 9:00 — 0 commitsWed 10:00 — 3 commitsWed 11:00 — 4 commitsWed 12:00 — 3 commitsWed 13:00 — 8 commitsWed 14:00 — 20 commitsWed 15:00 — 22 commitsWed 16:00 — 12 commitsWed 17:00 — 4 commitsWed 18:00 — 4 commitsWed 19:00 — 2 commitsWed 20:00 — 1 commitsWed 21:00 — 4 commitsWed 22:00 — 13 commitsWed 23:00 — 11 commitsThu 0:00 — 12 commitsThu 1:00 — 8 commitsThu 2:00 — 7 commitsThu 3:00 — 5 commitsThu 4:00 — 7 commitsThu 5:00 — 8 commitsThu 6:00 — 4 commitsThu 7:00 — 4 commitsThu 8:00 — 18 commitsThu 9:00 — 9 commitsThu 10:00 — 9 commitsThu 11:00 — 13 commitsThu 12:00 — 3 commitsThu 13:00 — 8 commitsThu 14:00 — 4 commitsThu 15:00 — 5 commitsThu 16:00 — 6 commitsThu 17:00 — 7 commitsThu 18:00 — 7 commitsThu 19:00 — 15 commitsThu 20:00 — 5 commitsThu 21:00 — 7 commitsThu 22:00 — 6 commitsThu 23:00 — 8 commitsFri 0:00 — 7 commitsFri 1:00 — 6 commitsFri 2:00 — 8 commitsFri 3:00 — 10 commitsFri 4:00 — 4 commitsFri 5:00 — 6 commitsFri 6:00 — 2 commitsFri 7:00 — 2 commitsFri 8:00 — 6 commitsFri 9:00 — 8 commitsFri 10:00 — 8 commitsFri 11:00 — 3 commitsFri 12:00 — 6 commitsFri 13:00 — 20 commitsFri 14:00 — 3 commitsFri 15:00 — 4 commitsFri 16:00 — 13 commitsFri 17:00 — 6 commitsFri 18:00 — 3 commitsFri 19:00 — 10 commitsFri 20:00 — 6 commitsFri 21:00 — 9 commitsFri 22:00 — 11 commitsFri 23:00 — 5 commitsSat 0:00 — 3 commitsSat 1:00 — 12 commitsSat 2:00 — 6 commitsSat 3:00 — 7 commitsSat 4:00 — 2 commitsSat 5:00 — 4 commitsSat 6:00 — 5 commitsSat 7:00 — 3 commitsSat 8:00 — 1 commitsSat 9:00 — 4 commitsSat 10:00 — 2 commitsSat 11:00 — 5 commitsSat 12:00 — 3 commitsSat 13:00 — 6 commitsSat 14:00 — 2 commitsSat 15:00 — 2 commitsSat 16:00 — 3 commitsSat 17:00 — 11 commitsSat 18:00 — 4 commitsSat 19:00 — 4 commitsSat 20:00 — 7 commitsSat 21:00 — 3 commitsSat 22:00 — 7 commitsSat 23:00 — 18 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Jul 11, 2026daily#6+3
  • public-apis/public-apis

    A collective list of free APIs

    500.5K stars · Python

  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript