AMD ROCm Grounded Web Agent

AMD ROCm Grounded Web Agent

Created by team Seeno on October 24, 2026
AgentOpsQwen3AMD ROCm

GroundedROCm is a 100% ROCm-native grounded retrieval engine powered by Qwen2.5-0.5B on AMD MI300X delivering verified JSON answers with zero hallucinations. Traditional search suffers from CUDA dependencies, high latency, API costs, and hallucinations. We solve it with a 5-stage local pipeline: Planner (Qwen2.5-0.5B via http://llama.cpp with fast-path for simple queries), Search Layer (Tavily / Qdrant / JSONL pluggable), Evidence Engine (deduplication + BM25 + compression), Synthesizer (warm http://llama.cpp server with schema-constrained JSON, max 96 tokens), and Guardrails (JSON repair + number/name grounding + URL validation). Result: 15MB binary via http://llama.cpp, small Docker size, ∼0.6s latency on MI300X, 98% grounding accuracy, 100% source validity, zero CUDA, zero external cost, instantly switchable to internal Qdrant for enterprise deployment.

Category tags:
Github
Explore more applications
Streamlit
application badge

testtinggg

good tingood tingood tingood tingood tingood tingood tingood tingood tingood tingood tin

LFG

AlpacaAI71AIML

Detonation Chamber

Run an untrusted npm/PyPI package, GitHub repo, or URL in a sealed, disposable Vultr sandbox. Watch what it does and get a verdict based on its actual behaviour. Every escape attempt is contained and recorded.

Builders Nepal

VULTR

Containment Foreman - sandboxed agent runtime

A human-gated foreman that plans AI agent tasks, dispatches each step to a disposable, network-less Docker sandbox, and returns verifiable receipts with SHA-256 artifacts, resource caps and zero host access.

Schultzenator

VULTR

Ghostfox Zero: Browser Agent

A sandboxed browser agent powered by our own Firefox engine. True agentic loop with vision verification, human approval gate, and MCP endpoint for AI agents.

autokeren

AgentOpsAIMLVULTR

LeakProof

Finds revenue leaks in billing exports without letting the data leak: model-written pandas runs in a throwaway gVisor sandbox on Vultr (no network, no secrets, hard limits), a second model checks every sentence, and each answer has a re-runnable receipt.

Design Master Solutions

VULTR