Discover the Best AI Resources

Microsoft Agent Framework

Builds production-grade AI agents and multi-agent workflows in .NET and Python, with graph-based orchestration for sequential, concurrent, and handoff patterns. Unifies Microsoft's Semantic Kernel and AutoGen lineages, adding durable, checkpointed runs.

SWE-bench Verified

A human-verified subset of 500 SWE-bench test cases for evaluating models that resolve GitHub issues into PRs using unit-test verification. Contains problem statements and base commits (pre-fix) for reproducible unit-test based evaluation; suitable for benchmarking code-fix and issue-resolution capabilities.

system_prompts_leaks

Archive of extracted and leaked system prompts behind major AI chatbots — Claude, ChatGPT, Gemini, Grok, Copilot, Perplexity and more — sorted by vendor and version with update dates, so you can read the hidden instructions and track how they change.

Computer Use Preview

Official reference code for building browser-controlling agents on Google's Gemini computer-use models. The model sees a screenshot, proposes a UI action, and the loop executes its clicks, typing and scrolling via local Playwright or cloud Browserbase.

Matrix-Game

Real-time, streaming world model for interactive long-horizon video and scene generation — provides persistent memory across interactions, streaming inference for live scenarios, and example demos for building interactive environments.

Pipedream

Exposes Pipedream Connect's 2,800+ APIs and 10,000+ pre-built actions to AI agents as MCP tools. OAuth stays server-side, so models act on a user's behalf without seeing their tokens. Ships HTTP/Streamable, SSE, and stdio transports.

DeerFlow

Orchestrates a lead agent, isolated parallel sub-agents, long-term memory, and sandboxes for long-horizon tasks — minutes to hours of deep research, coding, and content creation. LangChain/LangGraph-based with extensible skills; v2 is a full rewrite.

ChartGalaxy

Provides 1.7M+ synthetic and real infographic charts paired with their tabular data for training and evaluating multimodal models on infographic understanding, chart-to-table extraction, chart code generation, and example-based chart synthesis.

ContextForge

Federates MCP, A2A, and REST/gRPC backends behind a single gateway endpoint with centralized discovery, governance, and observability; optimizes agent and tool calling. Includes gRPC→MCP translation, plugin extensibility, OpenTelemetry tracing, and Kubernetes-ready deployment.

Y2A-Auto

Automatically transfers YouTube videos to AcFun and bilibili with an end-to-end pipeline: downloading, ASR, subtitle translation and QC, AI-generated metadata, content moderation, and automated uploads; includes a web dashboard and monitoring.

Presenton

Generates editable slide decks from prompts or uploaded documents and exposes an API for programmatic generation; self‑hosted (Docker or desktop), supports BYO LLM/image providers, and exports editable PPTX for full data control.

Dolphin

Converts document images—scans, photos, born-digital PDFs—into structured text in two stages: first map layout and reading order, then parse each element (text, tables, formulas, figures) in parallel, each guided by its own task prompt.