Search Results for "python 2"

iFixAi is an independent auditing toolkit for evaluating whether an AI agent performs the business job it was assigned. Instead of measuring only latency, token use, or prompt-injection resistance, it examines operational behavior, organizational alignment, and task outcomes. A standard run performs 32 inspections across five evaluation pillars and produces an A-to-F grade. Users can configure and launch audits through a guided CLI, explicit command flags, or an agent plugin and skill. The...

The Griptape framework provides developers with the ability to create AI systems that operate across two dimensions: predictability and creativity. For predictability, Griptape enforces structures like sequential pipelines, DAG-based workflows, and long-term memory. To facilitate creativity, Griptape safely prompts LLMs with tools (keeping output data off prompt by using short-term memory), which connects them to external APIs and data stores. The framework allows developers to transition...

Elephant Goldfish Model is an open-source collection of AI agent skills developed by Google for software architecture planning and specification reviews. It separates design work into two complementary roles with different levels of context. The Elephant agent uses project history, requirements, and earlier decisions to draft technical specifications. Independent Goldfish reviewers analyze the resulting documents without the original conversation context. This separation helps identify...

Sinas is an open-source platform for building AI applications without handing over your data. It sits between your applications and the LLM models, bringing AI agents, Python functions, database queries, state, files and permissions together behind one API, in an instance that belongs to you. Sinas runs in two ways on the same AGPL v3 code. Sinas Cloud is a managed service with upgrades, monitoring and backups handled for you, and a free plan that needs no credit card. Self-hosted, it runs on any Linux server or Kubernetes cluster. ...

ADR, short for Agentic AI Detection and Response, is an enterprise security system for monitoring and evaluating AI agents. It captures agent intent, tool activity, and execution traces from coding assistants, internal automations, and customer-facing agents. A normalized sensor layer provides observability across multiple agent tools and operating systems. ADR-Bench supplies more than 300 realistic tasks, 133 MCP servers, and coverage of 17 documented agent attack techniques. Its two-tier...

Mono Color Skill is an editorial image-generation system for posters, zines, portraits, packaging, publications, and visual field notes. It transforms a theme, phrase, object, article idea, or supplied photograph into an original print-inspired composition. The default look uses two controlled inks with one dominant plate and a narrowly assigned accent, while explicit monochrome requests stay pure one-ink. Images can use halftone, risograph grain, cyanotype exposure, or photocopy-style...

...The repository includes training code, model checkpoints, and infrastructure for both language modelling (via the ParlAI framework) and reinforcement learning for strategy agents. It supports two variants: Cicero (which handles full “press” negotiation) and Diplodocus (a variant focused on no-press diplomacy) as described in the README. The codebase is implemented primarily in Python with performance-critical components in C++ (via pybind11 bindings) and is configured to run in a high‐GPU cluster environment. Configuration is managed via protobuf files to define tasks such as self-play, benchmark agent comparisons, and RL training. ...