This repository is a comprehensive, curated bibliography and knowledge base for the field of active learning. It organizes hundreds of research papers by conference (ICML, NeurIPS, CVPR, etc.), journal (JMLR, TPAMI, etc.), thesis, and content topic (problem settings, deep active learning, applications, etc.). The repository also provides taxonomies, summaries, and links to papers. It is not a software application or data pipeline; it is a structured reference list intended for researchers and practitioners. The content is entirely in Markdown files, making it trivially reproducible and easy to navigate. The repository is actively maintained with recent commits and a growing star count.
Darwin-skill is a meta-skill (SKILL.md) and supporting tooling for autonomously optimizing agent skills (SKILL.md files). It implements a ratchet-based hill-climbing loop that evaluates skills across 9 dimensions (structure, effectiveness, meta-skill), spawns independent LLM judges for paired comparison, and only retains improvements validated by human-in-the-loop checkpoints. The repo includes a Node.js screenshot script for generating result cards, HTML templates, documentation, and references integrating Microsoft Research's SkillLens and SkillOpt papers. Despite being primarily a markdown document, it exhibits high craftsmanship: rigorous empirical grounding, explicit anti-pattern blacklist, versioned design philosophy, and detailed operational procedures. The actual executable code is minimal (one utility script), but the skill definition itself is a sophisticated artifact that demonstrates deep understanding of LLM evaluation pitfalls and optimization strategies.
CopilotKit is a comprehensive SDK and framework designed to integrate AI agents into user interfaces across web, mobile, and chat platforms. It functions as a middleware layer connecting frontend UI components (React, Vue, Angular) with backend agent frameworks (LangGraph, CrewAI, PydanticAI, etc.). The core value proposition lies in its ability to synchronize state between the agent and the UI, support generative UI (A2UI) for dynamic component rendering, and facilitate human-in-the-loop workflows. The repository is structured as a monorepo containing core runtime packages, framework-specific adapters, and an extensive suite of integration showcases. The architecture relies on a centralized runtime (`@copilotkit/runtime`) that handles agent connections via SSE and manages tool execution. Frontend interactions are managed through hooks (`useCopilotKit`, `useAgent`) that subscribe to the runtime. The codebase demonstrates a polyglot approach, supporting Python, TypeScript, Java, and C# backends alongside multiple frontend frameworks. While the core SDK is well-structured, the repository exhibits significant code duplication across its 20+ integration showcases, which serve as both documentation and regression tests.
The google/adk-go repository is a production-grade, open-source Go framework for building, orchestrating, and deploying multi-agent AI systems. It provides a comprehensive set of abstractions including agents, workflows, tool integrations, model backends (Gemini, OpenAI, Apigee), session management, artifact storage, and human-in-the-loop (HITL) support. The architecture centers around a workflow engine that supports graph-based execution with nodes, edges, retry, concurrency, and dynamic branching. It also implements agent-to-agent (A2A) and Model Context Protocol (MCP) for inter-agent communication. The framework is designed to be deployed via REST API, WebSocket, SSE, or as a console application, and includes launchers for Google Cloud Run and Vertex AI Agent Engine. While primarily an application framework, it also includes telemetry and analytics plugins for observability. The codebase is well-structured with extensive unit and integration tests, but some internal packages and experimental features (e.g., OpenAI model adapter) indicate ongoing development and potential for interface drift.
Pneumatic is an open-source SaaS workflow management system built with a Django backend and React/TypeScript frontend. The platform enables users to create workflow templates, execute workflows, manage tasks, collaborate with teams, and track progress through a comprehensive UI. It features multi-tenancy, payment processing (Stripe integration), notification systems, file attachments, reporting, and various third-party integrations. The architecture follows a microservices-like separation using Docker Compose, with distinct services for backend, frontend, database (PostgreSQL), caching (Redis), messaging (RabbitMQ), and file storage. The codebase demonstrates solid engineering practices with clear separation of concerns, though it shows some technical debt from using Django 2.2 and accumulated migration complexity.
SuperAgentX is a modular, open-source multi-agent AI framework designed for orchestrating autonomous agents that plan, act, and execute real-world workflows. It supports 100+ LLM providers (OpenAI, Azure, Gemini, Claude, Bedrock, Ollama, LiteLLM) and 10,000+ MCP tools via the Model Context Protocol. The architecture centers on `AgentXPipe` pipelines that sequence or parallelize agents, each composed of an `Engine` that wraps an LLM client and a set of tool handlers. Handlers are defined using a `@tool` decorator pattern that auto-generates LLM function schemas. The framework includes built-in human-in-the-loop approval channels (console, Slack, Teams), persistent memory with SQLite and vector stores (Chroma, OpenSearch), full observability via OpenTelemetry and SQL-based telemetry, and a CLI for project scaffolding. It also features a production-grade browser automation engine based on Playwright for tasks where APIs are unavailable.
ClawBands is a security middleware for OpenClaw AI agents that provides runtime interception with human-in-the-loop approval. It hooks into OpenClaw's plugin system to intercept tool executions (file operations, shell commands, network requests) and enforces policy-based decisions before allowing potentially dangerous actions. The system operates in two modes: terminal mode with interactive prompts, and channel mode (WhatsApp/Telegram) using a special response tool. Every decision is logged to an immutable JSON Lines audit trail, and statistics are tracked. The architecture features clean separation of concerns with distinct modules for policy interception, decision arbitration, approval queuing, logging, and storage.
This repository defines the Conversational Finance Governance Framework, an open specification (v0.4) for embedding runtime authority controls into conversational AI agents operating in fintech contexts. It includes a reference implementation (Lite sidecar) that demonstrates the control plane: classifying utterances along Financial Commitment Risk (F0-F3) and Regulatory Sensitivity (R0-R3) axes, binding each turn to an Action Object (inform/advise/commit/transact/represent), applying a decision table (FREE/AUTH/ESCALATE), enforcing classification assurance, issuing scoped credential records, and producing a hash-chained audit trail. The sidecar is a CLI tool that takes a product-line mapping YAML (payments, lending, insurance, collections) and an utterance, then outputs the governance decision as JSON. It does not call an LLM or execute real transactions; it is a control-plane demo. The repository also contains the full specification documents (v0.3 and v0.4), reference mapping files, and a test suite with gold-standard classification fixtures. The architecture is a monolithic CLI with a clean separation between classification, decision logic, and audit logging. The code is well-structured, uses dataclasses, and includes a reusable hash-chained audit log component. The last commit date (2026-09-09) appears to be in the future relative to the current date, which is anomalous but taken at face value indicates active maintenance.
Eko is a TypeScript framework for building production-ready AI agents that can automate workflows across browser, Node.js, and web extension environments. The core orchestration engine (Eko class) takes a natural language task, uses an LLM to generate a multi-agent workflow plan encoded as XML, then executes it with parallel/serial agent execution, replanning, and human-in-the-loop support. The system provides a clean abstraction over LLM providers (OpenAI, Anthropic, etc.) with retry and fallback, a ReAct tool-calling loop, and built-in browser automation agents that operate via screenshots or DOM labels. It also includes MCP client implementations (SSE, HTTP, stdio) for integrating external tools, and a chat agent for conversational interactions with tool delegation. The architecture is modular with separate npm packages: @eko-ai/eko-core (core engine), @eko-ai/eko-nodejs (Playwright-based browser agent), @eko-ai/eko-extension (Chrome extension agent), and @eko-ai/eko-web (web environment agent). The repository includes working examples (Chrome extension with side panel, Node.js automation using Playwright, and a React web app). The framework is designed for developers who want to automate complex, multi-step tasks using language models, with a focus on reliability, human oversight, and extensibility via custom agents and tools.