Add a health endpoint with a test
- Agents
- 2
- Sandboxes
- boat
- Secrets in boxes
- none
- Time
- 1m 20s
TaskWing turns one coding task into a team of AI agents, each working in its own sandbox, on any model you choose. You get back one pull request, with tests that prove it works.
Or in your terminal: taskwing run "add discount codes at checkout, with tests"
TaskWing splits your task into pieces, gives each piece to an agent in its own sandbox, and joins the work on one branch. You approve the checks, and you merge.
Workers never see the tests, and no agent grades itself. The exam decides.
Code goes in as a git bundle, and only commits come out. No GitHub login ever enters a box, and each box is scanned for secrets before it is deleted.
26 of 67 features built · Nov 2026
Claude now · GPT and open models next
Every run ends as a draft pull request
You approve the exam before any agent starts, and you merge the pull request at the end. Everything in between runs on its own.
Your coding agent splits the task into pieces that touch different files, and pins the public names so they fit.
Each piece gets a fresh sandbox and an agent. Code goes in as a git bundle, and only commits come out.
The pieces are joined on one branch. Hidden tests and every existing test run in a clean sandbox.
Your machine opens one draft pull request with the proof and the exam results. TaskWing never merges.
Agents that can see the tests learn to pass the tests. So a separate session writes the exam, and the tests stay out of every sandbox until the work is finished.
Who sees what
"A retry after a 500 returns 200." You approve the checks, not the code.
Neither does the lead. Only the clean exam box gets them.
A piece that breaks something that used to work fails the run.
TaskWing owns the part in the middle: splitting the work, running it in parallel, checking it, and handing it back. Models and sandboxes plug in.
Time, checks, pieces, and the pull request. These are from the first runs of the proof of concept in November 2026.
12/ 13
Hidden checks passed, graded in a clean sandbox that no worker could see into. Every check is written before any agent starts.
Fastest run
1m 20s
Task to tested pull request
4
Bugs proven
The 3 of 4 run failed on a field name the exam guessed. The lead now pins public names before the exam is written, and that failure is why.
$ taskwing hunt "the event bus and the repository" 1 Hunt 7 suspects, a failing test for each ✗ b3 delivers after Unsubscribe proven ✗ b4 non-UTC times miss the window proven · b5 passes today dropped 2 Pick 2 proven bugs. Start 2 fixers? y 3 Fix ■ ■ fixers get the bug, not the test 4 Exam ✓ b3 test ✓ b4 test ✓ existing tests 5 PR draft pull request opened
Point TaskWing at a part of your code. It writes a test for every bug it suspects and keeps only the tests that fail on today's code.
| Licence | AGPL-3.0, free |
|---|---|
| Engine | Go, runs on your machine |
| Desktop app | macOS, Linux, Windows · demo engine for now |
| Sandboxes | boat today · Docker, E2B and AWS planned |
| Models | Claude today · GPT and open models next |
| Each run ends as | 1 draft pull request · you merge |
| Status | Proof of concept, November 2026 · 26 of 67 features built |
TaskWing turns one coding task into a team of AI agents, each working in its own sandbox. You approve the exam first, and you get back one pull request, with tests that prove it works.
Yes. TaskWing costs $0 and is open source under the AGPL-3.0 licence. You bring your own agent and sandbox accounts, such as Claude Code and boat. The full source is on GitHub.
Each agent runs in its own sandbox: boat today, with Docker, E2B and AWS planned. Code goes in as a git bundle and only commits come out. No GitHub login ever enters a box.
The lead is your own coding agent, Claude Code today. GPT and open models are next, with each step routed to the model that suits it.
No, never. A run goes no further than 1 draft pull request with the proof and the exam results. You review it and you merge.
3 platforms: macOS (one universal build for Apple silicon and Intel), Linux and Windows. The Mac test build is about 4 MB. It runs on a demo engine until the engine stream ships.
A team of AI agents works on it in parallel, and you get back one tested pull request. Your machine, your models, your merge.