Manifest

Purpose: Managing and optimizing LLM API usage across multiple AI providers to reduce costs and avoid vendor lock-in.

Inferred · not functionally tested

Audience: developers and AI engineers managing LLM workloads

Inferred · not functionally tested

Functions: monitoring, workflow_automation

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: unknown · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: freemium · license: MIT · platforms: WEB · deployment: browser, self_hosted, cloud_managed, api_only

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: manifest.build · github.com. These links do not verify the individual claims.

Manifest sits in PulseGate's Inference & model serving category. Inferred · not functionally tested: It focuses on managing and optimizing LLM API usage across multiple AI providers to reduce costs and avoid vendor lock-in. Inferred · not functionally tested: It is built as a B2B product for developers and AI engineers managing LLM workloads. Basis unknown · not verified: A free plan is available; paid tiers begin at $19. Basis unknown · not verified: Manifest is available on the web and API, and it can be self-hosted.

Manifest builds and maintains Manifest, and it first shipped in 2022. Development happens publicly on GitHub with 7.1k stars and 1.3k commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are provider routing, cost tracking, and fallback rules. Inferred · not functionally tested: Catalogued interfaces include a public API.

Summary written by a language model from the project’s public pages.