# Agent tracing, monitoring and evaluation tools (slim)

> 10 agent observability & evals ranked by the Anchor benchmark. Leader Arize Phoenix (BB). Tools that trace agent runs, tool calls and model calls, and run evaluations on them. Compared on what appears in a trace, how fast a failure can be found, whether an evaluation can be reproduced, setup time and cost.

- Full: https://www.anchorterminal.com/categories/agent-observability.md (~3,050 tokens) · this version ~530 tokens · JSON https://www.anchorterminal.com/categories/agent-observability.json · canonical https://www.anchorterminal.com/categories/agent-observability
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

- Tools: 10 · agent-ready (BB+): 3 · accept x402: 0 · JSON: https://www.anchorterminal.com/api/v1/tools.json · by capability: https://www.anchorterminal.com/api/v1/capabilities.json
- Capabilities: obs.traces, obs.evals, obs.prompts, obs.gateway, obs.datasets

| # | Tool | Grade | Score | Confidence | x402 | Auth | Where | Slim |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 32 | Arize Phoenix | BB | 75.6 | medium | no | OAuth or key | local | https://www.anchorterminal.com/tools/arize-phoenix.min.md |
| 66 | Langfuse API + MCP | BB | 72.8 | high | no | API key | hosted | https://www.anchorterminal.com/tools/langfuse.min.md |
| 85 | LangSmith API + MCP | BB | 71.3 | medium | no | OAuth or key | hosted | https://www.anchorterminal.com/tools/langsmith.min.md |
| 165 | Respan API + MCP | B | 65.9 | medium | no | OAuth or key | hosted | https://www.anchorterminal.com/tools/respan.min.md |
| 229 | Braintrust API + MCP | C | 61.3 | medium | no | OAuth or key | hosted | https://www.anchorterminal.com/tools/braintrust.min.md |
| 298 | Laminar API + MCP | C | 57 | medium | no | API key | hosted | https://www.anchorterminal.com/tools/laminar.min.md |
| 310 | HoneyHive | C | 55.9 | medium | no | API key | hosted | https://www.anchorterminal.com/tools/honeyhive.min.md |
| 378 | Galileo API + MCP | D | 48 | medium | no | API key | hosted | https://www.anchorterminal.com/tools/galileo.min.md |
| 387 | Helicone AI Gateway + MCP | D | 47.1 | medium | no | API key | hosted + local | https://www.anchorterminal.com/tools/helicone.min.md |
| not ranked, shut down | Baserun | F | 7.3 | high | no | API key | hosted | https://www.anchorterminal.com/tools/baserun.min.md |