Qdrant is an Open-Source Vector Search Engine written in Rust. It provides fast and scalable vector similarity search service with convenient API.
Based on the limited social mentions provided, there isn't enough substantive user feedback to comprehensively summarize what users think about Qdrant. The social mentions consist mainly of YouTube video titles without actual user reviews or detailed discussions. The one HackerNews mention appears to be about a different AI agent runtime tool rather than Qdrant itself. To provide an accurate summary of user sentiment about Qdrant, more detailed reviews, forum discussions, or social media posts with actual user experiences would be needed.
Mentions (30d)
0
Reviews
0
Platforms
3
GitHub Stars
29,940
2,150 forks
Based on the limited social mentions provided, there isn't enough substantive user feedback to comprehensively summarize what users think about Qdrant. The social mentions consist mainly of YouTube video titles without actual user reviews or detailed discussions. The one HackerNews mention appears to be about a different AI agent runtime tool rather than Qdrant itself. To provide an accurate summary of user sentiment about Qdrant, more detailed reviews, forum discussions, or social media posts with actual user experiences would be needed.
Features
Use Cases
Industry
information technology & services
Employees
95
Funding Stage
Series B
Total Funding
$88.7M
1,590
GitHub followers
129
GitHub repos
29,940
GitHub stars
20
npm packages
40
HuggingFace models
423,508
npm downloads/wk
Show HN: Open-sourced AI Agent runtime (YAML-first)
Been running AI agents in production for a while and kept running into the same issues:<p>controlling what they can do tracking costs debugging failures making it safe for real workloads<p>So we built AgentRuntime, the infrastructure layer we wished we had. Not an agent framework, but the platform around agents:<p>policies memory workflows observability cost tracking RAG governance<p>Agents and policies are defined in YAML, so it's infrastructure-as-code rather than a chatbot builder. Example – agents and policies in YAML agent.yaml – declarative agent config name: support_agent<p>model: provider: anthropic name: claude-3-5-sonnet<p>context_assembly: enabled: true<p><pre><code> embeddings: provider: openai model: text-embedding-3-small providers: - type: knowledge config: sources: ["./docs"] top_k: 3 </code></pre> policies/safety.yaml – governance as code name: security-policy<p>rules: - id: block-file-deletion condition: tool.name == "file_delete" action: deny<p>CLI – run and inspect Create and run an agent agentctl agent create researcher --goal "Research AI safety" --llm gpt-4 agentctl agent run researcher agentctl runs watch <run-id><p>Manage policies agentctl policy list agentctl policy activate security-policy 1.0.0<p>RAG – ingest docs and ground responses in your knowledge base agentctl context ingest ./docs agentctl run --agent agent.yaml --goal "How do I deploy?"<p>Agent-level debugging agentctl debug -c agent.yaml -g "Analyze this dataset."<p>Cost tracking is exposed via the API (per agent/tenant), and the Web UI shows analytics. The workflow debugger (breakpoints, step-through) lives in the pkg layer; the CLI debug is for agent execution. What’s in there Governance<p>Policy engine (CEL) Risk scoring Encrypted audit logs RBAC Multi-tenancy Fully YAML-configurable<p>Orchestration<p>Visual workflow designer (React Flow) DAG workflows Multi-agent coordination Conditional logic Plugin hot-reload Workflow marketplace<p>Memory & Context<p>Working memory Persistent memory Semantic memory Event log<p>Context assembly combines:<p>policies workflow state memory tool outputs knowledge<p>RAG features:<p>embeddings (OpenAI or local) SQLite for development Postgres + vector stores in production<p>Observability<p>Cost attribution via API SLA monitoring Distributed tracing (OpenTelemetry) Prometheus metrics Deterministic replay (5 modes)<p>Production<p>Kubernetes operator (Agent, Workflow, Policy CRDs) Helm charts Istio config Auto-scaling Backup / restore GraphQL + REST API<p>Implementation<p>~50k LOC of Go Hundreds of tests Built for production (in mind)<p>Runs on: Local<p>SQLite In-memory runtime<p>Production<p>Postgres Redis Qdrant / Weaviate<p>Happy to answer questions or help people get started
View originalPricing found: $50
Show HN: Open-sourced AI Agent runtime (YAML-first)
Been running AI agents in production for a while and kept running into the same issues:<p>controlling what they can do tracking costs debugging failures making it safe for real workloads<p>So we built AgentRuntime, the infrastructure layer we wished we had. Not an agent framework, but the platform around agents:<p>policies memory workflows observability cost tracking RAG governance<p>Agents and policies are defined in YAML, so it's infrastructure-as-code rather than a chatbot builder. Example – agents and policies in YAML agent.yaml – declarative agent config name: support_agent<p>model: provider: anthropic name: claude-3-5-sonnet<p>context_assembly: enabled: true<p><pre><code> embeddings: provider: openai model: text-embedding-3-small providers: - type: knowledge config: sources: ["./docs"] top_k: 3 </code></pre> policies/safety.yaml – governance as code name: security-policy<p>rules: - id: block-file-deletion condition: tool.name == "file_delete" action: deny<p>CLI – run and inspect Create and run an agent agentctl agent create researcher --goal "Research AI safety" --llm gpt-4 agentctl agent run researcher agentctl runs watch <run-id><p>Manage policies agentctl policy list agentctl policy activate security-policy 1.0.0<p>RAG – ingest docs and ground responses in your knowledge base agentctl context ingest ./docs agentctl run --agent agent.yaml --goal "How do I deploy?"<p>Agent-level debugging agentctl debug -c agent.yaml -g "Analyze this dataset."<p>Cost tracking is exposed via the API (per agent/tenant), and the Web UI shows analytics. The workflow debugger (breakpoints, step-through) lives in the pkg layer; the CLI debug is for agent execution. What’s in there Governance<p>Policy engine (CEL) Risk scoring Encrypted audit logs RBAC Multi-tenancy Fully YAML-configurable<p>Orchestration<p>Visual workflow designer (React Flow) DAG workflows Multi-agent coordination Conditional logic Plugin hot-reload Workflow marketplace<p>Memory & Context<p>Working memory Persistent memory Semantic memory Event log<p>Context assembly combines:<p>policies workflow state memory tool outputs knowledge<p>RAG features:<p>embeddings (OpenAI or local) SQLite for development Postgres + vector stores in production<p>Observability<p>Cost attribution via API SLA monitoring Distributed tracing (OpenTelemetry) Prometheus metrics Deterministic replay (5 modes)<p>Production<p>Kubernetes operator (Agent, Workflow, Policy CRDs) Helm charts Istio config Auto-scaling Backup / restore GraphQL + REST API<p>Implementation<p>~50k LOC of Go Hundreds of tests Built for production (in mind)<p>Runs on: Local<p>SQLite In-memory runtime<p>Production<p>Postgres Redis Qdrant / Weaviate<p>Happy to answer questions or help people get started
View originalRT https://t.co/JBBn7XLEpq: Haystack, the #search #relevance #conference is coming to Berlin on 27 September. With a keynote by https://t.co/lTtfeY7Fp9, a presen… -- From Charlie Hull https://t.co/XuB
RT https://t.co/JBBn7XLEpq: Haystack, the #search #relevance #conference is coming to Berlin on 27 September. With a keynote by https://t.co/lTtfeY7Fp9, a presen… -- From Charlie Hull https://t.co/XuBTlUJLTV
View originalRepository Audit Available
Deep analysis of qdrant/qdrant — architecture, costs, security, dependencies & more
Yes, Qdrant offers a free tier. Pricing found: $50
Key features include: Expansive Metadata Filters, Native Hybrid Search (Dense + Sparse), Built-in Multivector, Efficient, One-Stage Filtering, Full-Spectrum Reranking, Qdrant Cloud, Qdrant Hybrid Cloud, Qdrant Private Cloud.
Qdrant is commonly used for: Build AI Search the Way You Want, Semantic Search.
Qdrant has a public GitHub repository with 29,940 stars.
Based on user reviews and social mentions, the most common pain points are: cost tracking.
