Work you can check.
A system of record for the spreadsheets and documents your AI edits, checked before every save.
First workbook free. Reading and writing workbooks costs nothing.
'%3e%3c/path%3e%3cdefs%3e%3clinearGradient%20gradientUnits='userSpaceOnUse'%20id='lobe-icons-codex-_R_0_'%20x1='12'%20x2='12'%20y1='3'%20y2='21'%3e%3cstop%20stop-color='%23B1A7FF'%3e%3c/stop%3e%3cstop%20offset='.5'%20stop-color='%237A9DFF'%3e%3c/stop%3e%3cstop%20offset='1'%20stop-color='%233941FF'%3e%3c/stop%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e "Codex"){kind=small}
Listed in the Claude Connectors Directory · MCP Registry · mcp.so, verified
Which are you?
For Claude Code, Codex, Cursor and any MCP agent
State your agent keeps, and the next session finds.
- Decision logs, task status, handoffs and results live in workbooks, not loose local files.
- Every write is a new version; a write made on an old version is refused, never merged.
- Edit a workbook like code: each write is compiled against its schema, with errors per cell.
- One line to connect: claude mcp add --transport http hedwigai https://mcp.hedwigai.com
For people and teams
Let Claude or ChatGPT keep your records right.
- Your spreadsheets and documents stay in Google Drive or Dropbox.
- Every edit is checked against the file's schema before it is saved.
- Every version is kept; an edit made on an old version is refused, never merged.
- Set up in the AI app you already use. The first workbook is free.
Try it now, nothing to install.
Who imports more?
Two US importers of the same product: guess which filed more shipments, from customs records.
Try it →Will your business plan work?
Every order your processes can run in, checked by TLC: where it breaks, the fix, and what it earns.
Try it →Push a neuron in Qwen3.5-4B
Pick one of 13 personalities, ask a question, and see the plain answer next to the pushed one.
Try it →Two characters, one neuron each
Give each a personality, set a scene, and watch them talk and move. Change one while it runs.
Try it →Solo agent against agent teams
Three setups tune the same kernel with 40 calls each, replayed call by call.
Try it →Train a small model on your examples
Give prompts and labels; Qwen3.5-0.8B gets new neurons fitted by least squares in about 10 seconds.
Try it →Can a monitor catch a pushed neuron?
A monitor reading Nanbeige4.3-33B's thinking ranks a pushed run above a plain one in 91 pairs of 100.
Try it →Does one neuron catch reward hacking?
The claim tested with controls, and the detector run on an answer of your own.
Try it →
01 · MCP for knowledge work
A compiler for knowledge work.
Your spreadsheets and documents stay in your Google Drive or Dropbox; the file is the record. Every AI assistant, and every run it starts, reads and edits that file through one layer, the workbook. Its schema declares each table's columns, types, required cells, keys and references, so the tooling that keeps code correct now keeps your operating records correct.
- Accurate
- Every edit is checked against the schema before it is saved. A change an assistant proposes is checked on a copy first and redone with the errors, so you are only asked to approve one that passes.
- Resilient
- Every version is kept and can be restored. An edit based on an old version, or over a file someone changed in Excel meanwhile, is rejected, never merged over.
- Fast and cheap
- An assistant reads and edits one table or section by its address, not the whole file, so a change costs only what it touches.
Works inside Claude, ChatGPT, Codex and Cursor.
Listed in
'%3e%3cpath%20d='M95%2015H75V155H95V15ZM255%2015H235V155H255V15ZM75%2025H65V125H75V25ZM265%2025H255V125H265V25ZM65%2035H55V95H65V35ZM275%2035H265V95H275V35ZM105%2075H95V155H105V75ZM235%2075H225V155H235V75ZM205%2085H125V185H205V85ZM125%2095H105V155H125V95ZM225%2095H205V155H225V95ZM75%20145H65V155H75V145ZM265%20145H255V155H265V145ZM125%20155H115V225H125V155ZM215%20155H205V225H215V155ZM85%20165H75V315H85V165ZM115%20165H105V315H115V165ZM225%20165H215V315H225V165ZM255%20165H245V315H255V165ZM105%20175H85V315H105V175ZM245%20175H225V315H245V175ZM135%20185H125V235H135V185ZM185%20185H145V195H185V185ZM205%20185H195V235H205V185ZM75%20195H65V275H75V195ZM145%20195H135V235H145V195ZM195%20195H185V235H195V195ZM155%20205H145V235H155V205ZM185%20205H175V235H185V205ZM125%20235H115V315H125V235ZM215%20235H205V315H215V235ZM145%20245H125V315H145V245ZM205%20245H185V315H205V245ZM185%20265H145V315H185V265Z'%20fill='white'/%3e%3c/g%3e%3c/svg%3e){kind=small}
A short answer from your workbooks and programs, with the source it rests on. Nothing to wait for.
Is Moderna a biotech with a public float above $5B?
Your agent
ask · Is Moderna NASDAQ:MRNA a biotech company with public float above $5B?
{
"answer": "yes",
"claims": [{ "figure": "public float", "value": "$9.6B",
"as_of": "2026-06-28" }],
"sources": ["MRNA 10-K, cover page",
"biotech-diligence-7fq2 · §Moderna"]
}Yes. Moderna's public float was $9.6B as of June 28, per the cover of its 10-K.
02 · Interpretability experiments
Why a model behaves as it does, measured inside it.
Interpretability explains a model's behaviour from its internals: which neurons and features respond to an input, and how the output changes as the input, the prompt or the environment changes. We test published claims on open-weight models with causal methods (ablation, activation steering, probes and weight edits), each against a control, and publish every number, including the claims that failed. You can rerun each one.
59 of 100
Does one neuron catch reward hacking?
The neuron posted as a reward-hacking detector in Qwen3.5-4B tells a hack from an honest answer in 59 pairs of 100. Another neuron, found with a held-out search, does it in 99.
Run it yourself →9.2% vs 8.6%
Does emergent misalignment run through one neuron?
Switching off the neuron that makes the model hostile leaves 9.2% of answers misaligned. A random control neuron gives 8.6%. The claim does not hold.
Run it yourself →91 of 100
Can a monitor reading the thinking catch a pushed neuron?
A Qwen3.5-9B monitor reading Nanbeige4.3-33B's chain of thought catches a full personality push in 91 pairs of 100, and a half push in 65.
Run it yourself →22 vs 7
Does a weight edit stop a model looping?
On prompts with no math, 22 of 32 answers from the released Qwen3.5-0.8B ran to the 8,192-token limit. The edited copy did it 7 times.
Run it yourself →Few example workbooks
VK2735 competitive landscape: the 8 closest obesity programs
Tirzepatide, CagriSema, retatrutide, orforglipron and four more against Viking's VK2735: phase, latest weight-loss readout, next catalyst and deals, every row cited.
29 sources · 25 minutes
Read the workbook →US importers of bulk black tea from India, from customs records
Four US buyers with the bills of lading that show it, who they buy from, what gates a new supplier, and the leads not worth chasing yet.
10 sources · 8 minutes
Read the workbook →Early-stage AI startups that filed a Form D in the last 30 days
Seven US AI companies raising in September 2026: the instrument each filing names, amount sold, investors and the people on it, each cited to the Form D on EDGAR.
17 sources · 13 minutes
Read the workbook →Tested on real work. Every score published.
Why agents quit early
Qwen3.5-9B never stops at an ordinary turn; right after the harness compacts the transcript, it stops about half the time.
| Measure | Qwen3.5-9B |
|---|---|
| Live runs that quit early | 3 of 4 |
| Stops at ordinary turns / after compaction | 0 of 192 / 0.49 |
Who imports it? Four workbooks that keep the answer, from US customs records
Marin Mountain Bikes filed more bicycle shipments than Giant or Trek; 572 companies imported black tea.
| Measure | US customs records |
|---|---|
| Most bicycle shipments | Marin Mountain Bikes, 5,711 |
| US black tea importers, 2026 | 572 |
Ten MCP registries and the use they can see: installs, pulls, connections and views
Cline and Docker count installs; the big directories count stars, their own page views, or nothing.
| Measure | Cline | Docker | Official registry |
|---|---|---|---|
| Servers listed | 199 | 316 | 62,550 |
| Counts per server | Installs, 1.47M in all | Pulls, Playwright 2.77M | Nothing |
Who earns on Stripe and who earns on x402: verified startup revenue against agent payments
81 of TrustMRR's top 100 are paid through Stripe, for $10.13M a month; all of x402 moved $1.77M in 30 days.
| Measure | Stripe (TrustMRR top 100) | x402 (all sellers) |
|---|---|---|
| Last 30 days | $12.89M from 81 startups | $1.77M from 14,073 sellers |
| Sellers with ten or more buyers | — | 44, for $0.84M |
How to train a private AI model on your own data and run it on-premise
Seven steps, from picking one check to running it in your building, and what a per-call API costs instead.
| Measure | 1,000 a day | 10,000 a day |
|---|---|---|
| Claude Haiku 5.5 API, a month | $10.50 | $105 |
| Claude Sonnet 5.5 API, a month | $210 | $2,100 |
Where does a business break when two things happen at once?
Six small businesses as TLA+ models. In each, the obvious fix still breaks and a second one holds.
| Measure | As written | Fixed |
|---|---|---|
| Restaurant, reward an episode | 22.99 | 37.83 |
| Coffee shop, reward an episode | -0.81 | 6.00 |
Questions, answered.
What does hedwigai do?
It is a system of record for the spreadsheets and documents an AI edits. Claude, ChatGPT, Codex, Cursor or any MCP agent keeps them as workbooks, optionally linked to a file in your Google Drive or Dropbox. Every write is a new version, a write made on an old version is refused rather than merged, and every edit is checked against the workbook's schema before it is saved.
Why keep an agent's state in hedwigai rather than a local file or its memory?
A local file stays on one machine and is overwritten by whoever writes last; an agent's memory is private to it. A workbook is found by the next session and by other people and agents, keeps every version, refuses a write based on an old version, and holds the shape its schema declares, so a tracker or a decision log does not drift.
How do I connect my agent?
In Claude Code: claude mcp add --transport http hedwigai https://mcp.hedwigai.com, then /mcp to sign in, or install the hedwigai plugin with /plugin marketplace add un-seen/hedwigai-skills. In Claude, add it from the Connectors Directory. Codex, Cursor, Hermes and any other MCP app add https://mcp.hedwigai.com as a server.
Where do my files live if I connect the MCP?
In your Google Drive or Dropbox, at the same path. The file is the record: a run reads the latest version first and writes each new version back to it. If someone changed the file in the meantime, the edit is refused rather than written over theirs, and every version can be restored.
Which AI apps does it work with?
Claude, where it is listed in the Connectors Directory; ChatGPT, where the plugin is in review; and Claude Code, Codex, Cursor, Hermes or any other app that adds an MCP server. It is also listed in the MCP Registry, on Glama and on mcp.so.
What does it cost?
The first workbook is free. Reading, searching and writing workbooks is free; research runs, started only when you ask for research, are billed to the account by what they use.