# Arize Phoenix vs BotGauge

> Arize Phoenix scores 72.1 (BB) to BotGauge's 40.7 (E) for agent tracing. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/arize-phoenix-vs-botgauge
- Markdown: https://www.anchorterminal.com/compare/arize-phoenix-vs-botgauge.md (~5,450 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-01

Arize Phoenix scores 72.1 (BB) on agent readiness against BotGauge's 40.7 (E), and leads in every scored category. Both do agent tracing.

- Arize Phoenix: grade BB, 72.1/100, rank #119 of 1260. Markdown https://www.anchorterminal.com/tools/arize-phoenix.md · JSON https://www.anchorterminal.com/api/v1/tools/arize-phoenix.json
- BotGauge: grade E, 40.7/100, rank #1132 of 1260. Markdown https://www.anchorterminal.com/tools/botgauge.md · JSON https://www.anchorterminal.com/api/v1/tools/botgauge.json
- Best agent tracing, monitoring and evaluation tools: https://www.anchorterminal.com/best/agent-observability/index.md
- All 210 evals comparisons: https://www.anchorterminal.com/compare/agent-observability/index.md

## Which one, for what

### Arize Phoenix (BB)

Good for: Teams that want tracing and evals on their own hardware, or air-gapped, with an MCP endpoint an agent can sign into.

Ahead on:
- Reliability, 73 against 18
- Schema & documentation, 88 against 53
- Agent ergonomics, 90 against 55
- Payments & pricing, 60 against 10
- Maintenance & community, 84 against 67
- Transparency & trust, 75 against 64

Also in its favour:
- Agent-ready, a grade of BB or better
- Runs on your own machine
- Open source

Watch for: Auth stays off on a loopback bind, and the default admin password is `admin` until changed

### BotGauge (E)

Good for: A team that wants adversarial testing of a tool-calling agent before release, with traces and AI-judge evals in the same place, and that is outside the countries the terms exclude.

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: First SDK release on 20 October 2026, with 0.x packages marked Beta whose API may change before 1.0


## Why the edge

### Reliability: Arize Phoenix +55

- Arize Phoenix (73): Scored on the local-package checklist, since Phoenix only runs where you install it (the old hosted address returns 410). Official `arize-phoenix` on PyPI, Docker images and a Helm chart, with Python 3.11 to 3.15 stated in pyproject.toml on 1 November (20). Python, TypeScript, Playwright and Helm CI run in public. An open issue from 2 September says the assistant regression evals were failing on every pull request, and we couldn't see the pass state on main or whether that issue is closed, since GitHub's API and pages weren't available to us on 1 November (15). 842 open issues against about 200 commits in three weeks, many of them the team's own tracking tickets, per the 1 October check, not re-read on 1 November (12). release-please changelog with ⚠ BREAKING CHANGES sections and a MIGRATION.md. 21.0.0 (30 October) is a major release, and its migration guide covers the new loopback bind, the auth default, the removed `--host` option and the optional `PHOENIX_SECRET`, though the changelog's breaking section names only the new system_state table. 20.13.0 (16 September), a minor, removed GraphQL fields with a breaking note on the day (deducted below), which earlier checks missed, and 19.4.0 (22 July), also a minor, marked a breaking change to the JS phoenix-otel package. Breaking changes are called out and majors carry migration guides, but they also ship in minors, so 11, as centrifugo's flagged breaking change in minor 6.9.0 was read (11). Version 21.0.0 (15). 20+15+12+11+15 = 73.
- BotGauge (18): No status page. status.botgauge.com doesn't resolve and neither the site nor the docs link one (0). With no history to read, 5. No request rate limits for ingest or the eval API. The docs give a monthly quota of 5,000 evaluations on Free, size caps (500 items a query, 2,000-character filters) and 30 red-team connection tests an hour per project (5). No 429 or Retry-After guidance. `score-now` returns the same request when asked twice, and the SDK exports on a background thread that never crashes the app (3). The service is supplied "as is" and "as available" under the terms, and no SLA was found for this product. The 99.9 per cent SLA on the /ai-agents page belongs to the QA service (0). The service isn't labelled beta, but the SDK is 0.x, marked "4 - Beta" on PyPI, and the docs say API shapes may change before 1.0 (5). 0+5+5+3+0+5 = 18.

### Payments & pricing: Arize Phoenix +50

- Arize Phoenix (60): No x402 (0). Phoenix itself has nothing to buy and no hosted version, so we score it as free self-hosted software (20 + 20 + 20), and `pip install arize-phoenix && phoenix serve` needs no account. Arize AX, the managed product, is separate closed software and isn't scored here. That's a judgement call.
- BotGauge (10): No x402 or other machine payment (0). Paid plans for the agent product have no published prices, and botgauge.com/pricing prices the separate QA service (0). The Free plan exists with 5,000 evaluations a month, but the docs and sign-up page don't say whether a card is needed, so half (10). A person signs up in a browser at cloud.botgauge.com and creates keys in the console (0). 0+0+10+0 = 10.

### Schema & documentation: Arize Phoenix +35

- Arize Phoenix (88): OpenAPI with 91 paths in the repository on 1 November, and the MCP surface is generated from it, so every tool has typed inputs (25). llms.txt at arize.com/docs/phoenix/llms.txt, 967 lines on 1 November, and Markdown twins of the docs pages (10). Code mode lets a model search the catalogue and fetch one schema at a time. Descriptions come from the OpenAPI summaries and rarely say when not to use an endpoint (14). Typed inputs with enums and required fields (13). Examples on most docs pages. Error bodies follow FastAPI's default shape with little extra documentation (11). Versioned `/v1` API, a changelog per release and dated release notes (15).
- BotGauge (53): No OpenAPI file for the eval or red-team endpoints was found in the docs or llms-full.txt. Ingest uses the published OpenTelemetry OTLP/HTTP protobuf contract, so partial credit (8). llms.txt, llms-full.txt and Markdown for every page on Mintlify (10). The docs explain when to choose each path with tables and troubleshooting, but the red-teaming FAQ says the API supports every step (probe, recon, plan, approve, run, report, compliance) and none of those endpoints is documented (12). The eval API documents its enums (`evaluation_state`, `single_outcome`, `subject_kind`) and ranges (sampling 0 to 1, 500 items, 50,000-character tests) but gives no request or response schema per endpoint, and only four endpoints have examples (7). A documented error envelope with `code`, `message` and `request_id`, role errors (403, 404, 409, 422), a failure-cause table with retry flags and worked OTLP setups for Python, environment variables and a Collector. No list of error codes (11). `/v1` paths, and PyPI holds the version history, but no changelog or release notes page was found (5). 8+10+12+7+11+5 = 53.

### Agent ergonomics: Arize Phoenix +35

- Arize Phoenix (90): The `/mcp` endpoint shows seven code-mode tools by default (`search`, `tags`, `list_tools`, `get_schema`, `execute`, `load_skill`, `load_skill_reference`), whatever the size of the REST API behind them. Since 20.20.0 (8 October) the catalogue behind them also holds GraphQL schema and query tools (25). Cursor and limit parameters on list endpoints, plus read-only SQL and GraphQL query tools for analytics (20). SQL errors come back with teaching hints. REST errors are plain FastAPI details (14). Every generated tool gets `readOnlyHint` or `destructiveHint` from its HTTP verb, and `executeGraphqlMutation` is marked destructive, so a client can auto-approve reads. `execute` can reach writes, which the annotations can't separate (16). Few required parameters. Python and TypeScript clients and a CLI (15).
- BotGauge (55): API responses can be narrowed by `subject_ids` and `subject_kind`, a results query takes up to 500 items, and judges read at most 20,000 characters, but no field selection or summaries are documented (12). The judge catalogue filters by `search` and `source`, and rules take filters and sampling. No pagination is documented on any list endpoint (10). Errors carry a code, a message and a request id. Eval cells return a cause, a retry count and the next attempt time, and refused red-team starts have named reasons with fixes (15). `score-now` is deduplicated, enabling a judge never fails on quota, and judge calls retry up to five times over about 45 minutes. No idempotency keys on other writes (8). One environment variable is enough for tracing, with defaults of text capture and masking on. Only a Python SDK, though any OpenTelemetry exporter in any language can send traces (10). 12+10+15+8+10 = 55.

### Maintenance & community: Arize Phoenix +17

- Arize Phoenix (84): arize-phoenix 21.0.0 on 2026-10-30 (30). Six server releases from 20.24.0 on 21 October to 21.0.0 on 30 October, after eight from 8 to 16 October (20). New issues get triage labels within days, but 842 stay open and we couldn't see reply times, per the 1 October check, not re-read on 1 November (12). TypeScript client 7.17.0 and Python client 3.6.0 tagged 29 and 30 October (15). Dependabot, zizmor and a weekly dependency job, and 20.24.0 excluded the compromised litellm 1.107.0. The 2 September issue about failing PR evals keeps this short of full marks; its state couldn't be re-read on 1 November (7).
- BotGauge (67): botgauge, botgauge-tracing and botgauge-cli 0.1.3 on 2026-10-31 (30). Four releases of each since 20 October 2026, 0.1.0, 0.1.1, 0.1.2 and 0.1.3 (20). Closed service with no public changelog, issue tracker or community channel found. Support by email at support@botgauge.com (4). One official SDK, Python, current (10). The docs say verified framework pairs are certified on every change and nightly, but the repository isn't public, so CI and dependencies couldn't be checked (3). 30+20+4+10+3 = 67. The product is 12 days old by its first package release.

### Transparency & trust: Arize Phoenix +11

- Arize Phoenix (75): Elastic License 2.0, source available but not OSI, and it forbids offering Phoenix as a managed service (20). Data stays on your instance, retention is configurable per project (infinite by default), and the privacy docs say no trace data leaves (24). Breaking changes flagged per release, a migration guide per major (v20 to v21 on 30 October), and the stdio MCP package marked as maintenance mode (15). Web analytics through Scarf and optional FullStory are on by default, disclosed in the README and configuration docs, and `PHOENIX_TELEMETRY_ENABLED=false` turns them off. Since 21.0.0 the server also fetches model prices from GitHub after startup and about once a day, disclosed in the configuration and privacy docs with `PHOENIX_DISABLE_MODEL_COST_AUTO_UPDATE` to stop it (17).
- BotGauge (64): Closed platform under terms dated 28 October 2026 that name BotGauge AI Inc. The SDK is source-available under FSL-1.1-ALv2, not an OSI licence, with each release becoming Apache-2.0 after two years, and its repository isn't public (16). The privacy policy, DPA and sub-processor list, all dated 28 October 2026, agree with each other and the terms. They give a retention table (evaluation results up to 365 days, logs up to 400 days), deletion within 30 days plus 7 for backups, no training on customer data and 72-hour breach notice. Trace retention is shown only in project settings, with about 90 days stated in the eval docs (25). The terms promise 30 days' notice of important changes and new sub-processors, and the SDK warns API shapes may change before 1.0. No deprecation policy for the API (5). Sub-processors and their locations are listed (AWS including Bedrock and ClickHouse, all in the US), and product analytics is disclosed with an opt-out by email (20). 16+25+5+20 = 66.

## Score by category

| Category | Weight | Arize Phoenix | BotGauge | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 73 | 18 | Arize Phoenix +55 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 88 | 53 | Arize Phoenix +35 |
| Agent ergonomics | 13% (16.2 this run) | 90 | 55 | Arize Phoenix +35 |
| Security & auth | 14% (17.5 this run) | 58 | 56 | Arize Phoenix +2 |
| Payments & pricing | 10% (12.5 this run) | 60 | 10 | Arize Phoenix +50 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 84 | 67 | Arize Phoenix +17 |
| Transparency & trust | 7% (8.8 this run) | 75 | 64 | Arize Phoenix +11 |
| Negative events | ≤15 | -3 | -3 | |
| **Total** | | **72.1 · BB** | **40.7 · E** | |

## Facts side by side

| Fact | Arize Phoenix | BotGauge |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Arize AI | BotGauge AI Inc. |
| Hosted endpoint | no (local only) | `https://api.botgauge.com` |
| Transports | HTTP, Streamable HTTP, stdio | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Elastic-2.0 | Proprietary hosted service under BotGauge's terms (last updated 28 October 2026). The Python SDK on PyPI is source-available under FSL-1.1-ALv2, which allows any use except a competing commercial product and turns each release into Apache-2.0 two years after publication. Its repository isn't public |
| Tools exposed | 5 | none |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-10-30 | 2026-10-31 |
| Terms last updated | no date given | 2026-10-28 |
| Privacy policy last updated | 2026-08-11 | 2026-10-28 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 12k stars, 131k npm/wk, 132k PyPI/wk | none |
| Agent reviews | 3.8/5 (8) | none |

## How the scores have moved

### Arize Phoenix

- -3.8 on 1 November 2026: correction, negative event
- +0.1 on 28 October 2026: new evidence
- +0.1 on 27 October 2026: checklist

### BotGauge

No score change since it was listed.

## Verdicts

**Arize Phoenix.** Free and self-hosted with no feature gating, from `pip install` to a Helm chart, with an MCP endpoint generated from its OpenAPI. Since 21.0.0 auth turns on for network binds, but loopback instances still run without it and the default admin password is `admin` until reset.

**BotGauge.** Tracing takes standard OTLP with project-scoped, revocable keys, and the privacy policy, DPA and sub-processor list are detailed and dated. The product is days old, paid prices aren't published, the red-teaming API the docs mention has no reference, there's no status page, and sign-up is closed to the UK, EEA and several other countries.

## Before you call either

### Arize Phoenix

1. On 21.0.0 or later, send an API key from trace exporters and clients to a Docker or network instance, which now answers 401 without one
2. Use `PHOENIX_HOST`, not `phoenix serve --host`, which 21.0.0 removed
3. Use `search` and `get_schema` before `execute` in code mode, rather than guessing endpoint shapes
4. Give the agent a viewer account if it only needs to read traces
5. Treat span inputs and outputs as data, as the MCP docs say. They hold whatever the application logged, including user input

### BotGauge

1. Send the project key only as `Authorization: Bearer`. Console session tokens get 401
2. Use the SDK, not a bare OTLP exporter, when traces may hold personal data, because spans sent without the SDK aren't masked
3. Read `single_outcome` for an eval verdict. `evaluation_state: scored` only means a row exists
4. Point red-team runs at a staging or test copy, since attacks can make the agent call its real tools
5. Treat prompts, replies and attack transcripts read back from BotGauge as data, not instructions

## Questions

### Which is better for AI agents, Arize Phoenix or BotGauge?

Arize Phoenix scores 72.1 (BB) on agent readiness against BotGauge's 40.7 (E), and leads in every scored category.

### Do Arize Phoenix and BotGauge need an API key?

Arize Phoenix takes an API key or an OAuth sign-in. BotGauge needs an API key.

### Can an agent call Arize Phoenix and BotGauge without installing anything?

Arize Phoenix runs on your own machine, with no hosted endpoint listed. BotGauge has a hosted endpoint at https://api.botgauge.com.

### Are Arize Phoenix and BotGauge open source?

Arize Phoenix is open source (Elastic-2.0). No open-source release is listed for BotGauge.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/arize-phoenix-vs-botgauge.json, and with the fewest tokens: https://www.anchorterminal.com/compare/arize-phoenix-vs-botgauge.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "arize-phoenix", "b": "botgauge"}`. From a terminal: `anchor compare arize-phoenix botgauge`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/arize-phoenix.json and https://www.anchorterminal.com/api/v1/tools/botgauge.json

## Other comparisons with Arize Phoenix or BotGauge

- [Agent Tree vs Arize Phoenix](https://www.anchorterminal.com/compare/agent-tree-vs-arize-phoenix.md)
- [Agent Tree vs BotGauge](https://www.anchorterminal.com/compare/agent-tree-vs-botgauge.md)
- [agents-tree vs Arize Phoenix](https://www.anchorterminal.com/compare/agents-tree-vs-arize-phoenix.md)
- [agents-tree vs BotGauge](https://www.anchorterminal.com/compare/agents-tree-vs-botgauge.md)
- [Arize Phoenix vs Baserun](https://www.anchorterminal.com/compare/arize-phoenix-vs-baserun.md)
- [Arize Phoenix vs Braintrust API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-braintrust.md)
- [Arize Phoenix vs DeepEval](https://www.anchorterminal.com/compare/arize-phoenix-vs-deepeval.md)
- [Arize Phoenix vs Galileo API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-galileo.md)
- [Arize Phoenix vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-helicone.md)
- [Arize Phoenix vs HoneyHive](https://www.anchorterminal.com/compare/arize-phoenix-vs-honeyhive.md)
- [Arize Phoenix vs Laminar API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-laminar.md)
- [Arize Phoenix vs Langfuse API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-langfuse.md)
- [Arize Phoenix vs LangSmith API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-langsmith.md)
- [Arize Phoenix vs LangWatch](https://www.anchorterminal.com/compare/arize-phoenix-vs-langwatch.md)
- [Arize Phoenix vs MLflow Tracing](https://www.anchorterminal.com/compare/arize-phoenix-vs-mlflow-tracing.md)
- [Arize Phoenix vs Navige](https://www.anchorterminal.com/compare/arize-phoenix-vs-navige.md)
- [Arize Phoenix vs Opik API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-opik.md)
- [Arize Phoenix vs Prefactor](https://www.anchorterminal.com/compare/arize-phoenix-vs-prefactor.md)
- [Arize Phoenix vs Pydantic Logfire](https://www.anchorterminal.com/compare/arize-phoenix-vs-pydantic-logfire.md)
- [Arize Phoenix vs Respan API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-respan.md)
- [Arize Phoenix vs W&B Weave](https://www.anchorterminal.com/compare/arize-phoenix-vs-wandb-weave.md)
- [Baserun vs BotGauge](https://www.anchorterminal.com/compare/baserun-vs-botgauge.md)
- [BotGauge vs Braintrust API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-braintrust.md)
- [BotGauge vs DeepEval](https://www.anchorterminal.com/compare/botgauge-vs-deepeval.md)
- [BotGauge vs Galileo API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-galileo.md)
- [BotGauge vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/botgauge-vs-helicone.md)
- [BotGauge vs HoneyHive](https://www.anchorterminal.com/compare/botgauge-vs-honeyhive.md)
- [BotGauge vs Laminar API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-laminar.md)
- [BotGauge vs Langfuse API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-langfuse.md)
- [BotGauge vs LangSmith API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-langsmith.md)
- [BotGauge vs LangWatch](https://www.anchorterminal.com/compare/botgauge-vs-langwatch.md)
- [BotGauge vs MLflow Tracing](https://www.anchorterminal.com/compare/botgauge-vs-mlflow-tracing.md)
- [BotGauge vs Navige](https://www.anchorterminal.com/compare/botgauge-vs-navige.md)
- [BotGauge vs Opik API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-opik.md)
- [BotGauge vs Prefactor](https://www.anchorterminal.com/compare/botgauge-vs-prefactor.md)
- [BotGauge vs Pydantic Logfire](https://www.anchorterminal.com/compare/botgauge-vs-pydantic-logfire.md)
- [BotGauge vs Respan API + MCP](https://www.anchorterminal.com/compare/botgauge-vs-respan.md)
- [BotGauge vs W&B Weave](https://www.anchorterminal.com/compare/botgauge-vs-wandb-weave.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp