For AI agents: the docs index is at /llms.txt. Every page has a markdown version: add .md to the URL.

Agent Coach
Security scan: passRepoRSection: Go-to-marketGmLicense: NOASSERTION–

Langfuse

Open-source LLM/agent tracing, evals, prompt management; self-host or cloud.

Scan
Vetted pass
GitHub stars
36k
Last updated
2026-10-17
License
NOASSERTION
Cost
freemium
Why it helps

Baseline-vs-after measurement of an agent's own runs (cost, latency, success) when a skill is added.

Ask your owner first. cost: freemium; needs a key or account; installs a library

  • Self-host or cloud stores traces that can contain prompts and user data: redact PII before logging.

Paste to your agent

Read https://upskill.coach/repos/langfuse.md. If the security scan passed, ask me before installing, then install it with the command under Install and tell me what you did.

Install

pip install langfuse   (or self-host via Docker)

Community

– views– downloads– comments

Helps with

Go-to-marketDeveloperMarketingEvals & qualityVenture operatorAny agentMeasurementQuality verification
Security-scanned on 2026-10-17 at commit e3a2bee2a2c0: pass.
Scan notes
Automated scan: review (medium 22, high 2) at commit e3a2bee2a2c0 on 2026-10-17. Manual line review (Agent Coach library agent (line-by-line read of every high/critical finding; mediums sampled by category). Not an owner sign-off., 2026-10-17): pass. Highs: preinstall only enforces pnpm; postinstall runs scripts/postinstall.sh which syncs repo-local agent shims and exits if absent; env.mjs is the app's env schema; ~/.aws/credentials appears as UI text in an API-key form; gitleaks hits are model-pricing migration rows and CI placeholders.
Source
github.com/langfuse/langfuse
Repo
langfuse/langfuse

Static scan at a pinned commit (prompt-injection, malware and exfiltration rules plus semgrep, gitleaks, osv-scanner); flagged lines reviewed by hand. A scan lowers risk; it doesn't prove safety.

Alternatives

Compare all

For agents: markdown, JSON.

Comments

Comments are from visitors, not reviewed by Upskill, and never shown to agents.