DeepSWE is a benchmarking platform that evaluates frontier coding agents on original, long-horizon software engineering tasks. It provides a public leaderboard, task examples, and tracks results across 113 tasks, 91 repositories, 5 programming languages, and 28 models.
Devv
Devv AI is an AI-powered search engine designed for developers, providing fast and accurate results to programming-related queries. Its GitHub repository is issues-only, used for bug reports, feature requests, questions and feedback about the tool.
Features
- AI-powered search engine for developers Source: github.com
Limitations
- issues-only repository for Devv AI Source: github.com
Links
Tags
-
0DeepSWE is a benchmarking platform that evaluates frontier coding agents on original, long-horizon software engineering tasks. It provides a public leaderboard, task examples, and tracks results across 113 tasks, 91 repositories, 5 programming languages, and 28 models.
-
0GitWit is described as an open source, AI-native coding platform intended for building ideas. The site also presents an AI Editor with AI-powered suggestions and real-time collaboration for building, testing, and deploying.
-
0Self-updating documentation for startups, enterprises, and agents.
-
0ZZZ Code AI is a website offering free AI-powered coding tools built on ChatGPT. It provides an answer tool for programming questions, a code converter, a code generator, and a code explainer, with specialized generators and explainers for languages such as Python, Java, C#, SQL, and HTML. Additional tools detect bugs, refactor, review, and document code.
-
0Supermaven is an AI code completion tool that uses a 1 million token context window to provide code suggestions. It is compatible with VS Code, JetBrains IDEs and Neovim, and includes a chat interface for working with models including GPT-4o and Claude 3.5 Sonnet. A free tier is offered, and Pro adds a 1 million token context window.
-
0Langfuse is an open source platform for tracing, evaluating and improving AI agents. It connects tracing, monitoring, datasets, experiments and evaluation in one continuous loop, capturing every LLM call, tool invocation and retrieval step. The platform includes prompt management, a playground, experiments and human annotation, and works with any language or framework supporting OpenTelemetry instrumentation.
Community notes
Reviews and discussion
No reviews yet
Be the first to share how this project worked for you.
Join the discussion
Sign in with a verified account to leave a review or join the discussion.
Sign in to review