BaseAI helps developers build serverless AI agents with memory, tools, and composable workflows for local development and deployment.
manifest.build
Manifest routes language model requests from agents to providers, with subscription, usage-based, and local model options.
About manifest.build
Manifest is an LLM gateway that routes requests from AI agents and workflows to different providers through a single OpenAI-compatible endpoint. It supports bring-your-own keys, subscription OAuth tokens, custom providers, and local servers such as Ollama, LM Studio, and llama.cpp, with per-route model parameter settings.
It provides automatic fallback to another provider, on-the-fly repair of malformed requests through Autofix, and tracking of requests, tokens, and cost by agent, key, and provider with full request and response body logs. A self-hosted Docker version can run on own infrastructure or a local machine.
Key features
- Single OpenAI-compatible endpoint for multiple models and providers
- Automatic fallback to another provider when one is down
- On-the-fly repair of malformed requests through Autofix
- Full request and response body logs for every call
- Routing to local servers including Ollama, LM Studio, llama.cpp
- Cost breakdown by agent, key, and provider
Best for: Builders and teams that route agent requests across multiple providers and need usage tracking.
Good for
- Supports bring-your-own keys, subscription tokens, custom providers, and local models
- Self-host option using Docker on own infrastructure or machine
- Shows token use and cost broken down by agent, key, and provider
manifest.build at a glance
- Website
- manifest.build
- Type
- Online tool
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
manifest.build alternatives
Tools and sites you could use instead, ranked by how closely they match.
Eden AI routes requests across language and other AI models through a unified API with provider options.
Replicate provides a cloud API for running and fine-tuning open machine learning models and deploying custom models.
Private AI for individuals, teams, and organizations. Workspaces, agents, models, and knowledge—one connected system on your terms.
TrueFoundry provides enterprise AI and MCP gateways for deploying, securing, and scaling models and agents.
LLM Gateway routes, manages, and analyzes requests across more than 40 language-model providers through one API.
Popular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioCoreWeavecoreweave.comKili Technologykili-technology.comAPI docsdocs.x.ai
manifest.build FAQ
Can I use Manifest with local models?
Yes, it routes to Ollama, LM Studio, llama.cpp or any local server, and lets you decide what goes to the cloud and what stays on your machine.
Can I self-host Manifest?
Yes, the router can run on your own infrastructure or machine using Docker.
What does Autofix do?
It repairs a malformed request before it returns to your agent, and is available through the gateway or standalone.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.