AgentFlow: In-the-Flow Agentic System Optimization

Deploy and share agents with open infrastructure, free from vendor lock-in.

Recipes and resources for building, deploying, and fine-tuning generative AI with Fireworks.

🐔 Agentic systems explained with chickens. Workflows, agents & orchestration made simple. Mermaid diagrams included

Ship 10x faster by running multiple Claude Code sub agents in parallel. GitHub-native orchestration for AI coding agents—no conflicts, no complexity, just pure parallelized productivity.

AI dev that actually gets things done

🤖 A composable framework for building AI applications.

An open-source framework for building monolithic or distributed agentic systems, ranging from simple LLM calls to compositional workflows and autonomous agents.

A production-grade Python client for the Swarms API, providing a simple and intuitive interface for creating and managing AI swarms.

Template for agentic Chat & Memory Agents with Dapr runtime, UV simplicity, and OpenAI Agents SDK.

Operationalizes PM insights through working agents grounded in GRC best practices. Provides prompt libraries and tools to identify governance and compliance risks before scaling programs, analytics initiatives, or AI systems.

Hardened Public Release of KAIROS invocation governance framework. Includes invocation terms, ethical compliance clauses, regulatory mapping, and sample outputs. Licensed under CC BY-NC-ND 4.0. License: Do not auto-generate via GitHub. Use hardened License.txt

TRuCAL: Truth-Recursive universal Correction Attention Layer An open-source PyTorch toolkit for real-time AI alignment and adversarial robustness. TRuCAL works via recursive attention masking, entropy-based vulnerability detection, and coherence loops to mitigate hallucinations and deceptive outputs without retraining. Maintained by The Clean Room.

Plarix Scan is a free GitHub Action that tracks real LLM API usage during CI (tests/build), calculates cost from provider-reported token usage, and posts a concise cost report on every pull request.

An infrastructure-level exploration of language, cognition, and trust in agentic systems

🎛️ Build efficient workflows with Deevs' Agent System, a plugin marketplace for Claude Code featuring multi-session chains and terminal control.

Contract-driven, agentic system for deterministic CAD generation from natural language using headless CAD

Structural vulnerability assessment: proxy signals and lawful authority extraction in agentic systems

A working UX systems prototype for agentic AI travel experiences, modeling explicit states, autonomy boundaries, confidence signals, and recovery patterns.

Lybrary can be dropped into any AI-assisted development workspace. It gives humans and agents a shared, well-structured home for Markdown documents, prompts, specs, and playbooks so context stays organized across experiments, sessions, and handoffs.