447 results. Find your next favorite, with a little help from the community.
Small, fast model in Anthropic's Claude 4.5 family for high-volume tasks; 200k-token context, supports extended thinking, priced $1/$5 per MTok.
Open-source autonomous coding agent (formerly OpenDevin) running in a sandboxed Docker environment; edits files, runs shell/browser tools, and calls LLMs.
Consumer AI companion app offering personalized text chat for friendship, emotional support, and roleplay; users customize a persistent avatar persona.
Mistral's flagship closed-weights dense LLM (~123B in v2), 32k context; French-built rival to GPT-4/Claude, available via la Plateforme and Azure AI.
Context compression layer that shrinks tool outputs, logs, files, and RAG chunks before they reach the LLM, achieving 20% fewer tokens for code and 60-95% fewer for JSON.
GitHub feature that auto-reviews pull requests, posting inline comments with suggested fixes; can be requested manually or set to review all new PRs.
Mistral's 22B code-specialized dense LLM under Mistral Non-Production License; supports 80+ programming languages, fill-in-the-middle and code completion.
30B/3B-active MoE (glm4_moe_lite) with 128K context, MIT license; small/fast GLM-4.7 tier for local and agentic coding with speculative decoding.
Consumer chatbot platform where users create and chat with user-defined persona bots; widely used for roleplay, companionship, and interactive fiction.
Codeium's VS Code-based AI IDE featuring the Cascade agent for autonomous multi-file edits, terminal execution, and codebase-wide context.
Meta's Llama 3.1 open-weight family with 8B, 70B, and 405B dense variants extended to a 128K token context, released under the Llama 3.1 Community License.
Smallest, fastest model in Anthropic's Claude 3 family for high-volume tasks; supports vision input and the Messages API. Retired April 2026.
Mistral's commercial mid-tier LLM served via API; modern line launched with Mistral Medium 3 targeting enterprise SOTA at ~8x lower cost, later refreshed as 3.1 and 3.5.
158B DeepSeek V4 Flash MoE with ~1M-token context, MIT license; smaller efficient tier of V4 designed for local and agentic inference workflows.
Cognition's autonomous software engineer that plans, writes, and debugs code inside a sandboxed VM with browser and shell, delivered as a cloud agent.
xAI's second-generation LLM, launched in beta on X with Grok-2 and Grok-2 mini; weights later open-sourced in 2025, using dense attention with MoE elements.
AI text-to-image generation service producing artwork from natural-language prompts; originally launched as an open beta operated through a Discord bot.
Text-to-image diffusion foundation with high-fidelity Chinese/English text rendering, Apache-2.0 license; supports style transfer, editing, and multi-aspect.
Mistral's small-tier LLM family; original API model launched with Mistral Large in 2024, later refreshed as the 24B Apache 2.0 open Mistral Small 3 and 3.1.
Task-centric AI workspace that turns a GitHub issue into a spec, plan, and multi-file edits, delivered as a reviewable pull request in the browser.
Gemini 3.5 Flash: fast agentic and coding model built for long-horizon tasks, rivaling flagship-model quality at Flash-tier latency and cost.
Open-source TUI/CLI coding agent maintained by the SST team; runs in a terminal, supports 75+ LLM providers via Models.dev, and offers session sharing.
Meta's third-generation open-weight LLM family with 8B and 70B dense variants, 8K token context, base and Instruct, under the Llama 3 Community License.
Sourcegraph's AI coding assistant offering chat, autocomplete, and edits in VS Code and JetBrains, using codebase-wide context via Sourcegraph search.