Logmera – Self-hosted LLM observability for AI apps

Name: Logmera – Self-hosted LLM observability for AI apps
Availability: InStock
Author: Thilakkumar

by Thilakkumar·Mar 5, 2026·1 point·2 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My Problem

LLM logging dashboard, but Langsmith and Llamaindex already do this.

Strengths

•Self-hosted storage eliminates vendor lock-in for sensitive AI logs.
•Simple Python SDK with direct API support requires minimal integration work.
•PostgreSQL backend allows custom queries and cheap long-term retention.

Weaknesses

•No built-in analytics, cost tracking, or advanced filtering beyond basic dashboard.
•Crowded space: Langsmith, Llamaindex, Arize, and Helicone offer richer features.

Similar Projects

Developer Tools●●Solid

Torrix, self hosted, LLM Observability,(no Postgres, no Redis)

Single Docker container with SQLite beats LangSmith's heavy Postgres dependency.

Solve My ProblemCozy

AdarshRao23

7441mo ago

Security●●●Banger

InferShield – open-source security proxy for LLM inference

LLM-specific threat detection (prompt injection, jailbreaks, exfiltration) that WAFs completely miss.

Solve My ProblemWizardry

Alex-Hosein

123mo ago

AI/ML●●Solid

Experience-engine – reflection-based memory layer for local LLMs

Turns chat history into structured 'belief' and 'cognitive pattern' blocks you can inject into prompts, with simple APIs like run_reflection and run_synthesis that read like a research prototype. It's smart about separating V1 (domain beliefs) from V2 (transferable cognitive patterns), but it's clearly early-stage — tiny repo, Ollama-only workflow, and few commits mean you should treat it as an experimental MVP rather than a drop-in production memory system.

Big BrainNiche GemShip It

ashishluthara

313mo ago

AI/ML●●Solid