Your research, not a chat
Questions, hypotheses, code, runs, samples and conclusions each have a place. Reopen a project and Home says where the work stopped and what is still open.
Eisoptric Workbench · Open source · A tool from Eisoptric’s research
Read the method, write the code yourself, run the experiment and read every sample. Eisoptric is organized around your questions, models, experiments and findings rather than around chats, and you decide how much the assistant may do.
Preview release, licensed under Apache 2.0. The builds are not code-signed yet: on macOS, approve the first launch in System Settings → Privacy & Security; on Windows, choose More info → Run anyway when SmartScreen warns. Works offline with local models.

Questions, hypotheses, code, runs, samples and conclusions each have a place. Reopen a project and Home says where the work stopped and what is still open.
The runtime listens only on 127.0.0.1, records are files you can read, and every request it sends is in a network log. Use API keys, your Claude or ChatGPT plan, or an offline model.
The whole interface is available in English and Traditional Chinese. Eisoptric follows the system’s language, or you choose in Settings.
Each screen holds one part of the work, and the assistant on every screen knows which one you are on. The screenshots show an example project.

Where the work stopped, what changed since you last looked, and what still needs a decision.

Your code, with the run, its cost, samples, findings and a terminal underneath. Notebooks open as cells.

Checkpoints and their fine-tuned branches, with a score followed along the line.

Frozen versions, runs and scores, and comparisons that say when they are not fair.

One sample across every model that saw it, the scorer’s word beside your label, and counterexamples kept.

Every file an experiment reads, whether it changed since it was frozen, and rows two files share.

Activations at every layer, patching against a random control, and sparse-autoencoder features.

Long work in its own worktree: what it may touch, its diff, then merge or discard.

Refusals and unexplained changes in one place, and what each backend can enforce.

The Python, packages and devices a run uses, kits to install, and SSH hosts for remote runs.
Each chat has a mode, chosen beside the assistant’s name. In all four, verdicts, labels, locks and merges stay yours.
You write the code. The assistant only reads and explains: an error, a change, a fix for you to type.
The assistant proposes changes, and each change or command waits for your approval.
The assistant works in the chat, on the project itself, and asks before anything sensitive.
The assistant works on the project and asks nothing. Work to keep apart goes to a task in its own worktree.
Modes and locks are a workflow constraint, not a security boundary: a shell in a task can still write a locked file, and Eisoptric records it afterwards on the Protection screen.
Eisoptric keeps what you asked, what you ran, what it measured and what you concluded together, so a number never gets separated from how it was produced.
01 / Home and Workspace
02 / Experiments
03 / Samples and Data
04 / Inspect
05 / Remote runs and existing results
06 / Assistant and Tasks
07 / Protection
08 / Resources and environment
A project’s questions, experiments, runs, labels and findings live in its own .workbench/research folder. Read them, diff them, commit them with your code.
my-project/ ├─ probe.py └─ .workbench/research/ ├─ questions/ ├─ hypotheses/ ├─ experiments/ ├─ versions/ ├─ models/ ├─ runs/<id>/samples.jsonl ├─ labels/ ├─ counterexamples/ └─ findings/
A project’s research records, next to its code.
macOS 12 or later on Apple silicon, and Windows 10 or later on x64.
Anthropic, OpenAI, Google and DeepSeek with your API key; Claude Code on your Claude plan; Codex on your ChatGPT plan; LM Studio for local, offline models.
Any Linux or macOS host you can reach over SSH, with the same Eisoptric version installed on it.
Research records are in the project’s .workbench/research folder. App data is in ~/.workbench-app. API keys are encrypted at rest, with the key in the macOS Keychain or Windows Credential Manager.
English and Traditional Chinese.
Apache License 2.0. Copyright Rick Weng.
Eisoptric Workbench is free for everyone. Download it, star the repository, open an issue, or send a pull request.