Free
Free
Apache-2.0 client with a self-hosted reference backend; managed assessment pricing was not verified.
- Access
- Apache-2.0 client with a self-hosted reference backend; managed assessment pricing was not verified.
Pheebs
● Identity checkedDeveloper Tools · Official-source review 2026-10-07
Pheebs is an open-source telemetry client for AI coding-agent workflows. Hooks in Claude Code, Cursor and Codex capture session events, tool timings, model changes and verification signals into local JSONL logs, with optional export to a self-hosted or managed backend. Reporting can examine verification practices, repeated rework and model-fit opportunities.
- Category
- Developer Tools
- Free access
- Apache-2.0 client with a self-hosted reference backend; managed assessment pricing was not verified.
- API access
- Documented backend routes include ingest, token validation, prompt classification and OTLP passthrough.
Is Pheebs right for you?
A good fit for
Choose it for engineering teams that want evidence about how coding agents are used and verified, with control over telemetry destination.
Before you choose
The default local logs avoid prompt text, source code and file paths. Optional prompt classification can send raw prompt text to your selected backend when enabled with consent. Published savings dashboards are illustrative and do not establish your team’s savings.
How to use Pheebs
Install the client and use its initialization and diagnostic commands to select coding agents. Leave the backend blank for local logging, or configure a reviewed endpoint and token. Examine coverage before interpreting rates and document whether prompt classification is enabled.
Telemetry privacy and reporting
A fresh install writes locally without a backend endpoint. Remote export requires both a base URL and token. Prompt classification is a separate exception: raw text can reach the configured backend while only the label is stored in local events. Treat task sizing and model-spend gaps as observations to investigate, rather than automatic routing or confirmed vendor-bill savings.
Review method and limits
Reviewed official product information on 7 October 2026. This listing describes documented workflows and billing, not a hands-on performance test. No account, device runner, generation or live customer session was used; confirm current terms before adoption.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Documented operating workflow | Install the client and use its initialization and diagnostic commands to select coding agents. Leave the backend blank for local logging, or configure a reviewed endpoint and token. Examine coverage before interpreting rates and document whether prompt classification is enabled. | Identity only | 2026-10-07 |
Understand the total cost
Pheebs pricing & plans
Alternatives to Pheebs
View all ↗
ConductorConductor runs parallel coding agents on Mac with optional Conductor Cloud sandboxes, multiplayer workspaces, mobile control, and an API. It orchestrates first-party Claude Code, Codex, Cursor, and OpenCode agents using your subscriptions and keys, with isolated microVMs for long-running cloud jobs.
Explore tool
cmuxcmux is a free, open-source macOS terminal built on Ghostty for multitasking with AI coding agents. It adds vertical tabs, split panes, notification rings, an in-app browser, and optional cloud VMs on paid plans for remote agent sandboxes.
Explore tool
CodeGPTCodeGPT is an AI coding agent extension for VS Code, JetBrains, and Visual Studio that supports multiple frontier models with BYOK or bundled credits. It emphasizes plan-then-build agentic workflows, MCP integrations, autocomplete, and team billing with pooled credits.
Explore toolThe practical questions
Frequently asked questions
Does Pheebs switch my model?
No. The vendor describes it as an audit tool that reads model-fit gaps and estimates opportunities. Model choices remain with the team.
Who is Pheebs a good fit for?
Choose it for engineering teams that want evidence about how coding agents are used and verified, with control over telemetry destination.
What is Pheebs used for?
Pheebs is an open-source telemetry client for AI coding-agent workflows. Hooks in Claude Code, Cursor and Codex capture session events, tool timings, model changes and verification signals into local JSONL logs, with optional export to a self-hosted or managed backend. Reporting can examine verification practices, repeated rework and model-fit opportunities.
Does Pheebs have a free plan?
Apache-2.0 client with a self-hosted reference backend; managed assessment pricing was not verified.. This record lists ongoing free access; check the plan limits before starting.
How much does Pheebs cost?
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use Pheebs through an API?
Documented backend routes include ingest, token validation, prompt classification and OTLP passthrough.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
The default local logs avoid prompt text, source code and file paths. Optional prompt classification can send raw prompt text to your selected backend when enabled with consent. Published savings dashboards are illustrative and do not establish your team’s savings.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Product documentation
Official product page reviewed for capabilities and practical constraints.
Read original source ↗Pricing and access
Apache-2.0 client with a self-hosted reference backend; managed assessment pricing was not verified.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.