Submit Tool
#

Code

AI tools tagged Code.

31 tools · handpicked & curated
// price
Atria Dawn Preview Shanghai AI Laboratory's open-weight agentic model for research and engineering
Gemini 3.8 Flash Cyber Google's Gemini 3.8 model tuned for finding and patching security vulnerabilities
Hy4 Preview Tencent Hunyuan's open-weight flagship, co-designed with its own dev tools
GPT-5.6 Cyber OpenAI's cybersecurity model for finding and closing vulnerabilities, restricted to vetted defenders
DeepSeek-V4-Flash-0731 DeepSeek's MIT-licensed 284B MoE model, retrained for stronger agentic coding
Gemini 3.5 Flash Cyber Google's Gemini 3.5 model tuned for finding and fixing security vulnerabilities
Muse Spark 1.2 Meta's coding-focused update to Muse Spark, shipped alongside its first terminal coding agent
Poolside Laguna S 2.1 Poolside's open-weight coding model that beats agentic coding rivals many times its size
Poolside Laguna XS 2.1 Poolside's smallest open-weight coding model, built to run on a single GPU
AlphaCode 2 DeepMind's competitive-programming model built on Gemini, ranking among top human competitors
Code Llama Meta's open-weight code-specialized Llama variant
CodeGen2 Salesforce's open-weight code model built for infilling and multi-turn program synthesis
Codestral Mistral's code-generation and completion model
Codestral Mamba Mistral's code model built on the Mamba state-space architecture instead of a transformer
CodeT5+ Salesforce's open-weight encoder-decoder code model family
Codex OpenAI's original code-completion model that powered early GitHub Copilot
DeepSeek Coder V2 DeepSeek's open-weight code-specialized mixture-of-experts model
DeepSeek-Coder-33B DeepSeek's earlier flagship code model, preceding DeepSeek-Coder-V2
Devstral Mistral's open-weight model tuned for agentic coding and codebase exploration
GLM-4.6 Zhipu's value-tier open-weight model for day-to-day coding
Granite Code IBM's open-weight code generation model family
Kimi K2.7 Code Moonshot's open-weight agentic coding model, tuned for tool-use and long-running tasks
Qwen2.5-Coder Alibaba's dedicated code model line, competitive with much larger general models on coding benchmarks
Qwen3-Coder Alibaba's open-weight agentic coding model
replit-code-v1.5 Replit's open-weight code-completion model
SantaCoder BigCode's small multilingual code model preceding StarCoder
StarCoder The original BigCode model that StarCoder2 later succeeded
StarCoder2 The BigCode collaboration's open-weight code generation model
Voyage-Code-2 Voyage AI's embedding model specialised for source-code retrieval
WizardCoder Microsoft's code-specialised fine-tune built with Evol-Instruct data generation
Yi-Coder 01.AI's open-weight code-specialized model