The AI Agent Index

Documenting the technical and safety features of deployed agentic AI systems

Aide


Basic information

Website: https://web.archive.org/web/20241224000855/https://aide.dev/blog/sota-bitter-lesson

Short description: A general-purpose software engineering assistant.

Intended uses: What does the developer say it’s for? Rapid general-purpose coding and software development.

Date(s) deployed: June 28, 2024 [source]


Developer

Website: https://web.archive.org/web/20241229171017/https://aide.dev/

Legal name: CODESTORY, INC [source]

Entity type: Corporation [source]

Country (location of developer or first author’s first affiliation): Incorporation: Delaware, USA (CODESTORY INC (7556925)) [source]. HQ: California [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; SOTA on SWEbench-verified uses Sonnet 3.5 [source] [source]

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’? Uses parallel single-trajectory exploration and reward rubrics to evaluate the agent’s tool actions [source].

Observation space: What is the system able to observe while ‘thinking’? Agent has file system, code, and terminal access. It can view progress via the generated rewards [source].

Action space/tools: What direct actions can the system take? The system accesses the following tools: List Files, Open File, Str_replace_editor, Attempt Completion, RipGrep search, Terminal Access [source]

User interface: How do users interact with the system? Agent is available in their extension and will soon be available on the AIDE editor [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? Closed source
  • Scaffolding: Is system scaffolding available? Closed source
  • Documentation: Is documentation available? Unavailable

Controls and guardrails: What notable methods are used to protect against harmful actions? Unknown

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: 62.2% on SWE-Bench verified beating the previous SOTA implementations [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

Ecosystem information

Interoperability with other systems: What tools or integrations are available? None

Usage statistics and patterns: Are there any notable observations about usage? Unknown


Additional notes

None