Writes C++. Proves it compiles, runs, and passes.
ByteAsk works in your terminal. It edits the code, runs the compiler, the sanitizers and your tests, and can drive the gdb session you already have open. You review the diff.
$ curl -fsSL https://code.byteask.ai/install.sh | shIt joins the gdb session you already have open.
Linux allows one debugger per process. If your gdb is attached, an agent that shells out to gdb gets Operation not permitted. ByteAsk connects through a bridge you start inside your own gdb, reads the live state, and asks before it runs anything that changes it.
Your gdb holds the process. A second debugger is refused by the kernel. ByteAsk goes through the bridge you started.
How a session is wired.
Check it yourself: while your gdb holds a process, run gdb -p <pid> in another shell.
An agent that shells out to gdb can run it in batch mode on a process nobody is debugging. It cannot join the session you are in, because Linux gives each process one tracer and that tracer is your gdb. ByteAsk connects through a bridge you start inside your gdb, reads the stop state, and proposes any command that would change it.
You get the tool's full output.
ByteAsk builds with your flags, runs the sanitizers, and runs your tests. It hands back the raw report with the frames, files and line numbers intact, so you can check the agent's reasoning against the same evidence.
==2967905==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x60c0000000c8WRITE of size 4 at 0x60c0000000c8 thread T0 #0 0x55d75c82e5a6 in OrderBook::cancel_all() demo/outputs/order_book.cpp:31 #1 0x55d75c82e5a6 in main demo/outputs/order_book.cpp:42 #2 0x7feead645249 in __libc_start_call_main libc_start_call_main.h:580x60c0000000c8 is located 8 bytes to the right of 128-byte regionallocated by thread T0 here: #0 0x7feeadcb94c8 in operator new(unsigned long)SUMMARY: AddressSanitizer: heap-buffer-overflow demo/outputs/order_book.cpp:31
Test project demo/outputs/build1/3 Test #1: book_ops ......................... Passed 0.00 sec2/3 Test #2: risk_engine ...................... Passed 0.00 sec3/3 Test #3: wire_codec ....................... Passed 0.00 sec 100% tests passed, 0 tests failed out of 3 Total Test time (real) = 0.01 sec
Nothing in these two blocks was typed by hand. They are what the tools printed.
Use our models, your key, or your own server.
- Managed
Sign in and use OpenAI, Anthropic and Google models through ByteAsk. No API key to paste.
byteask login- Your key
Use your own OpenAI, Anthropic or Gemini key. Traffic goes straight to the provider, not through ByteAsk.
byteask byok set- Your server
Point ByteAsk at vLLM, Ollama, llama.cpp, LM Studio, TGI, SGLang or a LiteLLM proxy. Self-hosted models are not metered.
byteask models add my-model --url http://your-host:8000
Reference documents it can cite
Seven built-in reference tools search these standards and datasheets and return the exact passage with a page citation. If there is no match, they say so instead of guessing.
| Tool | Corpus |
|---|---|
| autosar_ref | AUTOSAR C++14 · MISRA · ISO C++ |
| mcu_ref | STM32 · Cortex-M · Modbus · CAN |
| fpga_ref | Xilinx UltraScale · AMBA AXI |
| hft_ref | ITCH/OUCH · FIX · IEEE 1588 PTP |
| grid_ref | IEEE 1547 · 2030.5 · SunSpec |
| scpi_ref | SCPI · instrument manuals |
| x86_ref | x86-64 Software Developer Manual |
Install.
One command on Linux, macOS or Windows, or a plugin for your editor. Sign in with a link sent to your email.
Install
One line on Linux, macOS or Windows, or an editor plugin.
Sign in
A link is emailed to you. There is no password.
Run it in a repo
Describe the change. ByteAsk edits, builds and tests, then shows the diff.
Editors also on Windsurf and VSCodium via Open VSX. Every connector needs the byteask CLI on your PATH.
$ curl -fsSL https://code.byteask.ai/install.sh | shYour code stays yours.
Zero-retention by design. Your machine carries a short-lived token and nothing more.
Zero data retention
Your prompts and code are processed to answer the request, then dropped. Nothing is kept.
Not used to train models
Your repositories are not used to train any model. Ours or anyone's.
Passwordless sign-in
A signed magic link logs you in. No password to manage, and nothing to paste or leak.
Pricing.
Free to start. Paid plans add usage.
| Feature | Free | Pro | Max |
|---|---|---|---|
| Price | $0forever | $20per month | $100per month |
| Usage | Base monthly usage | 3x the usage of Free | 20x the usage of Free |
| C and C++ toolchain | Included | Included | Included |
| Sanitizers, gdb, and your tests | Included | Included | Included |
| Install with pip, uv, or npm | Included | Included | Included |
| Run priority | Standard | Priority runs | Highest priority runs |
| Support | Community support | Email support | Dedicated support |
| Get started | Get started | Start Pro | Go Max |
Free
Pro
Max
Self-hosted models are never metered by ByteAsk and do not count against your plan. With your own key, traffic goes directly to the provider.