SuperCoder 2.0
Basic information
Website: https://web.archive.org/web/20241228215004/https://superagi.com/supercoder/
Short description: Open source autonomous software development system [source]
Intended uses: What does the developer say it’s for? General-purpose coding and software development
Date(s) deployed: Earliest GitHub commits from July 3, 2024 [source]
Developer
Website: https://web.archive.org/web/20241228215051/https://superagi.com/
Legal name: SuperAGI, Inc [source]
Entity type: Corporation [source]
Country (location of developer or first author’s first affiliation): USA [source]
Safety policies: What safety and/or responsibility policies are in place? Unknown
System components
Backend model: What model(s) are used to power the system? Variable, including Claude 3.5 Sonnet and GPT-4o
Publicly available model specification: Is there formal documentation on the system’s intended uses and how it is designed to behave in them? None
Reasoning, planning, and memory implementation: How does the system ‘think’? It uses its “PlannerAgent, a sophisticated tool designed to navigate through the code files, identify buggy locations, and determine the necessary changes required to rectify the issues […] In some instances, the PlannerAgent may need to insert an entirely new method to resolve the problem or at least propose a viable solution”. SuperCoder 2.0 uses retrieval augmented generation and its ‘AssimilatorAgent’ to retrieve relevant files [source].
Observation space: What is the system able to observe while ‘thinking’? SuperCoder 2.0 looks at an entire codebase, using retrieval augmented generation and an agent to select specific files [source].
Action space/tools: What direct actions can the system take? SuperCoder 2.0 looks can retrieve, generate, and replace code in a codebase [source].
User interface: How do users interact with the system? They have a visual application user interface where a user can specify tasks for the agent [source].
Development cost and compute: What is known about the development costs? Unknown
Guardrails and oversight
Accessibility of components:
- Weights: Are model parameters available? N/A; backends various models
- Data: Is data available? N/A; backends various models
- Code: Is code available? Available [source]
- Scaffolding: Is system scaffolding available? Available [source]
- Documentation: Is documentation available? Available [source]
Controls and guardrails: What notable methods are used to protect against harmful actions? None
Customer and usage restrictions: Are there know-your-customer measures or other restrictions on customers? None
Monitoring and shutdown procedures: Are there any notable methods or protocols that allow for the system to be shut down if it is observed to behave harmfully? Unknown
Evaluation
Notable benchmark evaluations: “SuperCoder 2.0 achieves 34% success rate in SWE-bench Lite, ranking #4 globally and #1 among all open-source coding systems” [source].
Bespoke testing: None
Safety: Have safety evaluations been conducted by the developers? What were the results? None
Publicly reported external red-teaming or comparable auditing:
- Personnel: Who were the red-teamers/auditors? None
- Scope, scale, access, and methods: What access did red-teamers/auditors have and what actions did they take? None
- Findings: What did the red-teamers/auditors conclude? None
Additional notes
None