neuron-explorer
Qwen3.5‑4B 전용 조향형 뉴런 탐색기, 모든 MLP 뉴런을 밀어 결과를 보관·탐색
품질 에이전트를 대규모로 배포하고, Braintrust는 생산 추적·평가 실행·회귀 발생 전 감지하는 AI 가시성 플랫폼이다
Ship quality agents at scale. Braintrust is the AI observability platform for tracing production, running evals, and catching regressions before they reach users.
개발 도구Rust · TypeScriptGitHub @braintrustdata온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
Braintrust Coding Agent Plugins
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
Trace coding-agent sessions in Braintrust.
This monorepo contains the plugins and the shared Rust tracing daemon embedded
in the Braintrust CLI (bt). Plugins forward native events locally; the daemon
builds traces, journals events for recovery, and delivers spans to Braintrust.
Install your coding agent and the
Braintrust CLI,
then authenticate and enable tracing. For example:
Replace claude with your agent's CLI name below. Restart the agent after
setup and follow any plugin or hook trust prompts.
All six support bt trace enable, update, disable, and doctor.README 전문 보기 ↗Trace coding-agent sessions in Braintrust.
This monorepo contains the plugins and the shared Rust tracing daemon embedded
in the Braintrust CLI (bt). Plugins forward native events locally; the daemon
builds traces, journals events for recovery, and delivers spans to Braintrust.
This repository also packages the Braintrust
plugin for submission to
the official ChatGPT and Codex plugin directory. It connects to Braintrust's
hosted MCP server through OAuth and requires no bt installation. Installing it
does not enable session tracing.
Install your coding agent and the Braintrust CLI, then authenticate and enable tracing. For example:
bt login
bt trace enable claude --project my-coding-agent
Replace claude with your agent's CLI name below. Restart the agent after
setup and follow any plugin or hook trust prompts.
All six support bt trace enable, update, disable, and doctor.
| Agent and setup guide | CLI name | One-off traced run | Import / live attach | Distribution |
|---|---|---|---|---|
| Google Antigravity | antigravity | — | Yes | GitHub |
| Claude Code | claude | Yes | Yes | GitHub |
| Codex | codex | Yes | Yes | GitHub |
| Cursor | cursor | Yes | Yes, transcript-limited | GitHub |
| Grok | grok | — | — | GitHub |
| OpenCode | opencode | Yes | — | npm |
| Pi | pi | Yes | — | npm |
Use run to trace one invocation, import to trace a saved session, or
import --attach to follow an active transcript:
bt trace run --project my-coding-agent claude -- -p "summarize this repository"
bt trace import claude SESSION_ID
bt trace import claude SESSION_ID --attach
bt trace run --project my-coding-agent cursor
bt trace import cursor SESSION_ID --attach
See the agent guides for limitations.
bt trace doctor claude
bt trace status
bt trace update claude
bt trace disable claude
doctor shows which configuration is in use and whether the running tracing
daemon can authenticate it. status reports trace delivery.
update keeps your settings; disable removes the plugin and its settings.
For command hooks, bt trace hook exits nonzero when it cannot capture an
event. Exit 0 means the daemon accepted the event into its journal; delivery
can still fail later. Use bt trace status --session-id <ID> or doctor to
inspect those later failures. See hook exit status
for the full contract.
src/plugins/<agent>/content/ Plugin source copied into distribution builds
src/runtime/js-daemon-client/ Shared JavaScript event-forwarding client
src/skills/ Shared skills included in plugin builds
bt-daemon/ Rust daemon, translators, and integration tests
scripts/ Shared build and publishing tools
.github/workflows/ CI and release automation
Use Bash and Python 3 for plugin scripts, Node.js 24 and pnpm 11.21.0 for the JavaScript packages, and stable Rust for the daemon. Run from the monorepo root:
make build # Build all plugins into dist/<agent>
make build-codex # Build one plugin
make codex-submission # Validate and build the MCP-only OpenAI ZIP
make test-codex-packaging # Test Codex packaging and release contracts
make test-codex-mcp-loading # Check installed MCP loading with a local Codex CLI
make test # Build and validate plugin packages and forwarders
cargo test --manifest-path bt-daemon/Cargo.toml --all-features --locked
Real-agent tests require installed agents and are run separately; see the test harness guide. See the daemon README for architecture and local debugging.
Edit plugin sources here. The per-agent GitHub distribution repositories and npm packages are generated artifacts. See AGENTS.md for the release PR and approval workflow, sandbox publishing, and npm release workflows.