249 listed
Agent infrastructure
The services agents run on: memory, code sandboxes, browsers, voice, search and scraping APIs, vector databases, LLM gateways, inference, durable execution and hosting. Facts such as self-hosting and compliance come from each vendor's own pages, with links.
Showing 1–20 of 20
- 0.840score
Supermemory
Supermemory
Memory and context engine for AI that extracts facts, keeps user profiles and feeds context back to agents.
InfrastructureAFreshness: A★ 31.4Kmemory - 0.821score
Prefect
Prefect Technologies
Durable orchestration for data, ML and agent workflows, written as Python functions.
InfrastructureAFreshness: A★ 24.1Kdurable execution - 0.799score
Browserless
Browserless
Headless browsers that run on Browserless cloud or in your own Docker deployment, reached over WebSocket and REST.
InfrastructureAFreshness: A★ 13.8Kbrowser - 0.772score
Unstract
Zipstack
Platform that uses LLM prompts to turn unstructured documents into structured JSON, deployable as an API or ETL pipeline.
InfrastructureAFreshness: A★ 7.3Kdata - 0.742score
Metorial
Metorial
MCP gateway that gives company agents approved tools, role-based access and a record of every call.
InfrastructureAFreshness: A★ 3.4Khosting - 0.719score
DBOS
DBOS
Durable workflows and queues that run on Postgres, for backends and AI agents.
InfrastructureAFreshness: A★ 1.6Kdurable execution - 0.694score
Portkey AI Gateway
Portkey
AI gateway giving one API to 250+ models, with observability, guardrails and prompt management.
InfrastructureCFreshness: C★ 13.3Kgateway - 0.600score
Linkup
Linkup
Web search API for AI applications, available through one API call or deployed inside your own cloud.
InfrastructureAFreshness: Asearch - 0.599score
Bland AI
Bland AI
Voice AI agents for regulated, high-stakes phone calls, run end to end on Bland's own speech, language and voice models.
InfrastructureAFreshness: Avoice - 0.599score
Deepgram Voice Agent API
Deepgram
One real-time API for voice agents combining speech-to-text, LLM orchestration and text-to-speech, priced at $4.50/hr.
InfrastructureAFreshness: Avoice - 0.599score
xpander.ai
xpander.ai
Governed platform for every agent, model and tool a company runs, deployable in its own cloud.
InfrastructureAFreshness: Ahosting - 0.597score
Daily
Daily
Global WebRTC infrastructure and SDKs for realtime voice and video, from the team behind Pipecat.
InfrastructureAFreshness: Avoice - 0.597score
Langbase
Langbase
Serverless platform to build, deploy and scale AI agents with memory, RAG and hosted tools.
InfrastructureAFreshness: Ahosting - 0.597score
Pipedream Connect
Pipedream
Managed auth and 10,000+ prebuilt tools for AI agents, across 3,000+ APIs.
InfrastructureAFreshness: Ahosting - 0.596score
Pipecat Cloud
Daily
Hosted platform for deploying and scaling Pipecat voice and multimodal agents, with autoscaling and observability.
InfrastructureAFreshness: Avoice - 0.596score
Requesty
Requesty
AI gateway and OpenAI-compatible router for 600+ models, with routing, failover, caching and observability.
InfrastructureAFreshness: Agateway - 0.596score
Scrapfly
Scrapfly
Web scraping, cloud browser, screenshot, extraction and crawler APIs under one API key, with managed proxies.
InfrastructureAFreshness: Ascraping - 0.596score
Turbopuffer
turbopuffer
Search database for vector and full-text queries, built on object storage and available as a Python client.
InfrastructureAFreshness: Avector db - 0.594score
Cerebrium
Cerebrium
Real-time AI infrastructure for deploying voice agents, video models, LLMs and other AI workloads, with autoscaling.
InfrastructureAFreshness: Ainference - 0.571score
LlamaParse
LlamaIndex
AI parsing tool that turns complex documents, tables and charts into clean markdown at scale.
InfrastructureAFreshness: A★ 65data