AcruxCore
Open-source LLM ops platform: prompt versioning, an AI gateway, automatic tracing, a tool catalog, and evaluation, all self-hostable.
AcruxCore is a multi-tenant LLM-ops platform that replaces the usual spreadsheet-plus-logging-library-plus-eval-script setup with one tool. Version and diff prompts with Jinja2-style templating, route every model call through a single AI gateway (OpenAI, Anthropic, Gemini and more) with caching and retries, get an automatic trace for every gateway request with no extra instrumentation, register reusable tools the gateway can execute, and run evaluations against a dataset to compare prompt versions. It ships under Apache 2.0, self-hosts with one docker compose command, and is free to use hosted at acruxcore.com while in beta (bring your own model provider keys).
Key Features
- Prompt versioning with Jinja2-style templating
- Unified AI gateway for OpenAI, Anthropic, Gemini and more
- Automatic request tracing, no extra instrumentation
- Reusable, versioned tool catalog
- Dataset evaluation and scoring
- Gateway response caching and retries
- Audit log included by default
- TypeScript and Python SDKs
- One-command self-hosting with Docker Compose
Use Cases
- Version and promote prompts to production
- Route LLM calls through one gateway endpoint
- Debug LLM requests with automatic tracing
- Evaluate prompt changes against a dataset
- Build and reuse tools across prompts and agents
- Self-host an LLM-ops platform on your own infrastructure
Pros
- Open source, Apache 2.0, no gated enterprise features
- One-command self-hosting via Docker Compose
- Gateway sits in the request path, so tracing needs no extra instrumentation
- Real Jinja2-style templating with conditionals and loops
- Audit log on by default, not behind an upgrade
- Free to use while in beta
Cons
- New project, small community so far
- Single-team only, no organization/project hierarchy yet
- Fewer third-party integrations than established platforms
AcruxCore Alternatives
Explore similar tools and alternatives
Looking for alternatives to AcruxCore? Here are some similar tools you might like:
Langfuse
Open-source LLM observability platform for tracing, debugging, and evaluating AI application performance in production and development.
Helicone
LLM observability platform that logs every API call, tracks costs, and monitors latency via a one-line proxy integration - YC W23.
Braintrust
AI evaluation and testing platform for LLM applications with experiment tracking, human annotation, automated scoring, and production tracing.
Opik
Open-source LLM tracing and evaluation platform by Comet ML - logs every LLM call, runs automated quality metrics, and integrates with CI/CD to catch regressions before production.
MLflow
Open-source MLOps platform by Databricks for tracking ML experiments, versioning models, and managing deployment pipelines, with 20k+ GitHub stars.
Ready to try AcruxCore?
Visit the official website to explore all features and get started with AcruxCore today.
Reviews
0 reviews for AcruxCore
Based on 0 reviews
Share your experience
Log in to write a review for AcruxCore
Ito
Only code review that runs your code. Provides runtime analysis with evidence (logs, video, screenshot) to show how code changes application actually work. Back-end, front-end, api, integration.
Cursor
AI-native code editor built on VS Code with built-in AI chat, autocomplete, and codebase understanding.
GitHub Copilot
AI pair programmer by GitHub/OpenAI that suggests code completions, functions, and entire files in your IDE.
Have an AI Tool?
List your AI tool for free, or go featured for top placement in your category - and reach thousands of potential users.
Submit Your Tool