Every AI provider (OpenAI, Anthropic, Google and dozens more) has its own API format, so an app that wants to use several models — or switch when a cheaper or better one comes along — normally has to write and maintain separate integration code for each. Requesty removes that friction: it's a single, OpenAI-compatible endpoint that routes a request to whichever of 600+ models across 30+ providers you specify, so switching providers becomes a config change instead of a rewrite. Requesty is a managed, Rust-built LLM gateway routing requests across 600+ models from 30+ providers including OpenAI, Anthropic, Google, DeepSeek and Mistral through one OpenAI-compatible API. It offers intelligent routing, prompt caching claimed to cut token costs up to 90%, and enterprise governance features (SSO, RBAC, audit logs, model whitelisting). Pricing is straightforward: a Free tier (200 requests/day, free models only), Pay-As-You-Go (a flat 5% markup on underlying model costs, no subscription or seat fees, $10 free credit on signup), and custom Enterprise pricing with SOC2/GDPR/HIPAA compliance and EU data residency.
| # | Tool | Best for | Price |
|---|---|---|---|
| 1 | Développeurs | — | |
| 2 | Développeurs | — | |
| 3 | Développeurs | — | |
| 4 | Équipes d'ingénierie et entreprises produit voulant intégrer des agents de codage autonomes sans perdre le contrôle de leurs données, identifiants ou infrastructure. | — | |
| 5 | Développeurs et ingénieurs ML sur Mac Apple Silicon voulant exécuter localement de gros modèles de langage sans matériel cloud ni GPU dédié. | — | |
| 6 | Entreprises de secteurs réglementés (défense, secteur public, finance) ayant des exigences strictes de résidence des données et ne pouvant pas utiliser d'API tierces. | — | |
| 7 | Développeurs construisant des agents IA nécessitant un support multi-fournisseurs LLM et une intégration éditeur | — | |
| 8 | Équipes et développeurs individuels utilisant plusieurs harnais d'agents IA (Claude Code, Cursor, Gemini CLI, GitHub Copilot CLI...) | — | |
| 9 | Entreprises B2B avec un produit établi cherchant à être citées par les IA génératives (ChatGPT, Perplexity, Gemini, Claude) plutôt que par Google | — | |
| 10 | Développeurs, équipes IA et entreprises comparant le coût des modèles IA avant de choisir un fournisseur | — | |
| 11 | Équipes de développement et utilisateurs d'agents de codage IA qui évaluent des frameworks de spec-driven development. | — | |
| 12 | Équipes de développement standardisant des règles de code entre plusieurs agents de codage IA. | — |
An open-source conversational API that enables autonomous AI agents to execute coding work in isolated sandboxes with access to repositories, tools, and credentials. Self-hosted platform for agent orchestration with streaming output and multi-turn convers
A Swift-based inference engine that enables running the 125-billion parameter Qwen 3.8-Flash-Next model on Apple Silicon Macs with limited memory by streaming expert weights from storage. Achieves approximately 12 tokens/second on 48GB M-series Macs.
Self-hosted AI platform for distributed, multi-model LLM inference on Kubernetes clusters with single-command installation and air-gapped deployment support.
Open-source Rust runtime for building AI agents that can call multiple LLM providers, run tools safely, and plug into terminals, CLIs, or editors like Zed and Claude Code.
A shared home for AI coding agent sessions, prompts, and tool calls, so teams can search, share, and pick up each other's agent work across different harnesses.
Done-for-you optimization service that helps B2B companies get cited and recommended by AI systems like ChatGPT, Perplexity, Gemini, and Claude.
A free, real-time pricing tracker that compares nearly 1,000 AI models across 17 providers, so you can see who's actually cheapest before you build.
Open, community-maintained directory tracking spec-driven development frameworks and real-world projects to evaluate their practical effectiveness.
Define coding rules once as version-controlled Markdown, then auto-generate the config files Cursor, Claude, GitHub Copilot, and other AI coding agents expect.
