660 tools
Free planAI models & APIs
NobodyWho is a Rust-based local inference engine with bindings for Python, Kotlin, Swift, React Native, Flutter and Godot. It combines GGUF language models, structured tool calling and local speech/vision capabilities for application developers.
Free to startAI models & APIs
Ramp Router provides one model endpoint with automatic fallbacks, request-level observability and configurable privacy controls. It selects models by workload and performance requirements to help teams inspect inference costs.
Free planChatbots & assistants
Local runs chat, file questions, meeting transcription and coding workflows on an Apple Silicon Mac. It selects models by chip and memory, keeps editable memories and offers Office Mode plus optional cloud-model keys.
Free planAI agents & automation
Actx0 stores agent sessions and extracts compact memories for semantic retrieval before the next model reply. Managed workspaces include knowledge search, memory consolidation, keys, audit events and usage tracking.
Free tier unknownAI models & APIs
TrustedRouter exposes an OpenAI-compatible model gateway with provider routing and privacy constraints. It publishes route-specific prices and attestation information and supports prepaid, BYOK and usage billing.
Free planCoding & development
Revalvo compares prompts across model providers in a browser workbench. It adds immutable prompt versions, dataset runs, configurable scorers and exportable reports with cost and latency metrics.
Free planAI models & APIs
oMLX is an Apache-2.0 model server and native Mac interface built on MLX. It persists model cache blocks to SSD, serves multiple model types and provides compatible endpoints for supported coding clients.
Free tier unknownAI models & APIs
Gemini Omni 1.1 Flash adds video scene extensions, start/end keyframes and resolution controls to the Gemini developer ecosystem. Google documents access through AI Studio and the enterprise Agent Platform API.
Free tier unknownAI models & APIs
Gemini 3.5 Transcribe provides streaming and recorded-audio transcription in Google developer platforms. Google documents custom vocabulary, disfluency cleanup and recorded speaker attribution with timestamps.
Free planAI agents & automation
Aramb combines model routing, voice, browser execution, sandboxes, memory, tool integrations and usage billing for AI-agent products. It supports no-code authoring and developer integration within a shared credit system.
Free tier unknownAI models & APIs
WeatherNext 3 is Google’s global AI weather model using satellite observations and hourly updates. It supplies forecast data through Google products and cloud data services, including variables relevant to renewable energy.
Free tier unknownAI models & APIs
Gemini 3.8 Flash is Google’s model for reasoning, coding and agent workflows. The related Flash Cyber variant focuses on defensive vulnerability research and patching with restricted trusted-defender access.
Free tier unknownAI models & APIs
Atlas is World Labs’ multimodal world model for generation, reconstruction and space-time simulation. It combines text, images, video and 3D context to produce new views and explicit spatial outputs.
Free planAI models & APIs
ARBR is an MIT-licensed control plane that routes model requests through an OpenAI-compatible endpoint. It offers cost attribution, budgets, guardrails, evaluations and provider fallback policies.
Free planAI agents & automation
Viso Now creates computer-vision agents from natural-language descriptions and video. Users refine detection behavior and connect cameras or other systems; enterprise Viso Suite adds broader deployment and governance.
Free planAI models & APIs
Desert Ant Labs provides compact on-device models and native SDKs for tasks such as speech processing, recognition and redaction. Its catalog includes platform-specific integration examples and several beta models.
Free tier unknownAI models & APIs
SWE-2 is Cognition’s coding model for multi-step software engineering tasks. The official release describes multiple reasoning-effort levels and availability through Devin Desktop and CLI, with rollout to Devin Web and Fusion.
Free tier unknownAI models & APIs
Twigg stores conversations, assembles context for each model and routes requests across supported LLM providers. Applications create a chat and send subsequent events rather than resending full conversation history.
Free tier unknownCoding & development
Lloyal is a TypeScript runtime for composing local models and agent behaviors inside applications. It describes shared attention state, agent abilities and deployment through desktop, CLI and web application surfaces.
Free tier unknownAI models & APIs
Gemini 4 Argon is Google’s announced model for complex coding, enterprise knowledge work and cyber-defense workflows. Its launch article describes long-running tasks and a larger output-token limit.
Free tier unknownAI models & APIs
Google’s Gemini 3.8 Flash TTS and Flash-Lite TTS models generate speech with directed character voices and scene dialogue. The announcement describes developer access through the Gemini API and Google AI Studio.
Free tier unknownAI models & APIs
Gemini 3.8 Live and Live Extended Thinking are Google dialogue models for real-time voice interactions, visual context and tool use. Extended Thinking targets more complex, multi-step tasks while maintaining a live conversation.
Free tier unknownAI models & APIs
Claude Fable 5.1 is Anthropic’s model for coding and knowledge work, introduced alongside the more selectively available Mythos 5.1. The official announcement documents API availability and changes to cached-context pricing.
Free planCoding & development
Promptic provides OpenTelemetry-based LLM tracing, prompt optimization and evaluations against a team’s own datasets and business metrics. It supports model comparisons, API/SDK access and credit-based platform usage with bring-your-own model keys.
Showing 72 of 660 tools
Plan facts carry individual sources and check dates. Unknown values are excluded from required filters.