What Tablif read on Wicklee's site
Wicklee describes itself as: “Wicklee — Private AI, finally observable.”
- Price model: free tier
- Free tier: Free forever
- Stage: Live, no waitlist
- How it differs: “Built to complement your existing Prometheus / Grafana / Datadog stack rather than replace it.”
What it is
Calls itself “GPU fleet monitoring”.
- Calls itself: GPU fleet monitoring
“GPU fleet monitoring for local AI inference”
Where it puts itself
Rules out “Prompts and responses are never read, stored or transmitted”.
- Says it will not: Prompts and responses are never read, stored or transmitted
“Built to complement your existing Prometheus / Grafana / Datadog stack rather than replace it.”
“Prompts and responses are never read, stored or transmitted”
What it costs
A free tier, free forever. Has an enterprise plan.
- Free plan: free forever
- Enterprise plan: yes
“The agent is open source, free forever and works on its own: full dashboard at localhost:7700, unlimited”
“Enterprise runs the entire control plane on your own infrastructure.”
Who it sells to
Sells to developers. Built for enterprise.
- Sells to: developers
- Company size: enterprise
“Best-node selection API, reactive automation webhooks, performance CI/CD, and an MCP server so AI agents can query your fleet's status”
“Enterprise runs the entire control plane on your own infrastructure.”
How it runs
A command-line tool. Runs locally and works offline. Can be self-hosted. Offers an API. Open source. AI is the core of the product.
- Kind: cli
- Runs where: on the device, offline · self-hosted
- API: yes
- Open source: yes
- AI role: core to the product
“Open-source agent that tracks GPU power, thermals and tokens/sec for Ollama and vLLM nodes, with a local dashboard”
“…full dashboard at localhost:7700, unlimited local nodes”
What it works with
Integrates with Datadog, Grafana, Ollama and 2 more.
- Integrates with: Datadog · Grafana · Ollama · +2
“Built to complement your existing Prometheus / Grafana / Datadog stack rather than replace it.”
“Open-source agent that tracks GPU power, thermals and tokens/sec for Ollama and vLLM nodes”
What it offers as proof
Live, no waitlist. Try it without signing up. Publishes docs and a blog.
- Trial asks for: nothing
“Installs in 60 seconds — no sudo, no account, nothing to configure.”
“Documentation -> https://wicklee.dev/docs”
Sources
Tablif read these pages, last on 17 Oct 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- Scalattice: OpenAI-compatible inference on a distributed GPU network
- Lifeboat: Run 2–6x more agents on the GPU you already have
- Kure Monitor: Kubernetes AI monitoring and pod failure detection
- VYRE OS & Apps: Local AI on your hardware. One connected ecosystem.
- Beacon: See your AI agents execute in real time.
- Dorbit: Dedicated inference with low-cost GPUs
- GPUDealer: Find. Sell. Request. Used GPUs, AI servers, memory
- PROMETHEUS: Safe AI Dev & Scan Security: Run AI agents locally. Every plugin scanned before execution