neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻譯準備中
Local-first control plane for AI coding agents — launch browser terminals, run and remotely control sessions, and track files, tokens & cost across Claude Code, Codex, Cursor, Gemini CLI and 20+ more. 100% local, no telemetry.
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
The exact tokens your AI provider billed you — cache splits,
reasoning tokens, long-context surcharges — reconciled across 40
coding tools, entirely on your own machine. Nothing you build here
ever leaves your machine unless you opt a node into it.
If SuperBased catches something useful in your next bill, a star helps
other people looking for the same thing find it.檢視完整 README ↗npx @superbased/observer
No install, no config, no network. It reads the session logs your coding agents already keep on disk, prints a 30-day cost table by tool and model, and deletes its temporary database on exit.
One local binary that tracks Claude Code token usage, Codex cost and Cursor spend side by side, and helps you control them.
~/.observer/.observer guard simulate replays your history before you turn on enforcement.| SuperBased | ccusage | CodeBurn | Langfuse | Helicone | LiteLLM | |
|---|---|---|---|---|---|---|
| Built for | Coding-agent cost & control | CC/Codex cost meter | Local CC spend + budget toolkit | LLM-app observability | LLM-app observability + gateway | AI gateway |
| Coding tools covered | 40 adapters | Claude Code, Codex, + companion pkgs | 31-36 per their own docs | Instrument-per-app | Instrument-per-app | Anything routed through it |
| Provider-reported (not estimated) tokens | ✓ via local proxy | Partial (from logs) | Partial (from logs) | ✓ (SDK) | ✓ (proxy) | ✓ (proxy) |
| Cache 5-min vs 1-hour write split | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ |
| Reasoning + long-context surcharge accounting | ✓ | Partial | Partial | Partial | Partial | Partial |
| Runs 100% local, no cloud required | ✓ | ✓ | ✓ (opt-in team-sync preview) | Self-host a stack | Self-host or SaaS | Self-host |
| Agent-queryable memory over your history (MCP) | ✓ | ✓ (usage MCP) | ✓ | ✓ (trace MCP) | ✗ | ✗ |
| Cross-tool session handoff | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ |
| License | Apache-2.0 | MIT | MIT | MIT (core) | Apache-2.0 | MIT |
Checked against each project's public repo (July 2026). Each of these tools is good at what it was built for; the full comparison covers more tools and when to pick which.
| Channel | Command |
|---|---|
| npm | npm install -g @superbased/observer |
| PyPI | uv tool install superbased-observer (or pipx install / pip install) |
| VS Code | code --install-extension superbased.superbased-observer (Cursor, VSCodium and Windsurf: Open VSX) |
| Installer | curl -fsSLO https://github.com/superbasedapp/observer/releases/latest/download/install.sh && sh install.sh |
Every channel ships the same prebuilt, pure-Go binary for Linux (x64, arm64), macOS (Intel, Apple
Silicon) and Windows x64. The installer (Windows: install.ps1) also offers smaller editions
(minimal, developer, managed), checks each archive against SHA256SUMS and its Ed25519
signature, never runs sudo, and supports offline installs with --from-dir. Run
sh install.sh --help for every option.
observer start # proxy + watcher + dashboard; opens http://localhost:8081
observer scan # backfill history from the session logs already on disk
observer claude / observer codex, or ANTHROPIC_BASE_URL=http://localhost:8820.observer init also registers the MCP server so your agents can query their own
history (it adds tool schemas to every turn, so it stays opt-in).observer doctor checks the install; observer status shows what has been captured.
localhost:8081): Overview, Live, Sessions, Cost, Plans & limits, Cache, Security, Settings and
more, filterable by tool and project, and readable on a phone.observer <tool> --continue-from <session> handoffs.observer statusline, and a CLI for everything (observer usage, cost, predict, tail).Supported agents include Claude Code, Codex, Cursor, Copilot and Copilot CLI, Gemini CLI, Cline and Cline CLI, Antigravity, OpenCode, OpenClaw, Pi, Hermes, Kilo Code, Qwen Code, Kiro CLI, Kiro Crew, Crush, Kimi Code, Grok, Devin, Aider, Qoder, goose, droid, Open Interpreter, Command Code, Junie, Poolside, Zed, Mistral Code, Muse, Prime Agent, DeepSeek, zcode, Freebuff, Cowork and Grok Bot, plus ChatGPT, Claude, Gemini, Copilot and Perplexity on the web through an optional browser extension. Per-tool setup: superbased.app/docs/track.
Click any session to open its detail view. Four of its tabs:
SuperBased sends no telemetry and needs no account. It stores paths, commands and short excerpts,
scrubs secrets before anything is written, and binds the proxy and dashboard to 127.0.0.1 by
default. The proxy forwards your own requests, unchanged, to the provider you already use. Remove
everything with observer uninstall --all --purge. Details: PRIVACY.md.
Running coding agents across a whole engineering org? SuperBased also offers central visibility across developers, budgets and policy, and SSO sign-in. See SuperBased for organizations or write to [email protected].
Questions go to Discussions, bugs and adapter requests to Issues, and security reports through SECURITY.md. Pull requests are welcome: see CONTRIBUTING.md (building needs Go 1.26+, no CGO). If SuperBased saves you a surprise bill, a star helps others find it.