Explore the directory

A library for training speculative-decoding draft models that deploy directly into LLM inference engines such as vLLM, speeding up inference without changing output quality.

• Models
• Inference

A curated list of open-source projects where LLMs research markets, make trading decisions, or connect agents to market data, organized into agents, MCP servers and skills.

• Curated lists

An IntelliJ-based IDE plugin that generates a git commit message from the current diff using a configurable LLM provider, with a customizable prompt template.

• Editors
• Git

An agentic CI/CD gate that reviews a code diff, fixes confirmed findings in sandboxes, re-reviews the result, and requires passing repository checks before it opens a pull request.

• Code quality
• CI/CD

A local security audit tool for AI API relays and LLM proxies that checks for prompt injection, model substitution, tool-call rewriting, response-stream anomalies and credential-related risk.

• Security

A Chinese-language study roadmap for LLM application development, covering RAG and agent projects with runnable code, interview preparation notes and a paper-reading skill.

• Tutorials

A sample serverless chat application with retrieval-augmented generation, built with LangChain.js, Azure Functions, Azure Static Web Apps and Azure Cosmos DB as the vector store.

• RAG
• Hosting

A book on neural networks and large language models for natural language processing, covering machine learning foundations through pre-training, generation, prompting, alignment, inference and reasoning.

• Books

An open-source benchmark that evaluates browser AI agents on everyday online tasks such as booking travel, ordering food and applying for jobs, across a set of live websites.

• AI evals
• Browser automation

A desktop app that runs multiple pi coding-agent tasks side by side, each in its own thread or git worktree, with an integrated review, terminal and file workbench.

• Coding agents

A full-stack framework for building, running and shipping AI agents, bundling tool discovery, memory, security, multi-tenancy, human approvals and observability behind a single Python decorator.

• Agent frameworks

A remote MCP server exposing Jina AI's Reader, Search, Embeddings and Reranker APIs as tools, including web page reading, web and academic search, screenshot capture and semantic deduplication.

• MCP servers
• RAG

A community-curated directory of MCP servers that TensorBlock turns into a hosted, searchable registry, with structured profiles, install-config previews and a free public API for each indexed server.

• MCP servers
• Curated lists

A local-first, zero-trust agentic IDE that keeps code, git, a terminal, a browser, models and MCP tools inside one durable desktop workspace, with approval and review surfaces for sensitive actions.

• Coding agents
• Editors

A code generator for Go that produces type-safe struct converters from interface definitions, avoiding reflection at runtime.

• CLI tools

A curated list of open-source repositories and papers on training language, vision-language, and agent models with on-policy distillation and on-policy self-distillation, organized by teacher source, supervision signal, and training-pipeline stage.

• Curated lists
• Papers

An open-source generalist agent harness for enterprise use, combining OpenAPI and MCP tool integration, configurable reasoning modes, and policy-based guardrails for task execution on the web and APIs.

• Agent frameworks

A plugin marketplace of Power BI and Microsoft Fabric skills, subagents and hooks that teach Claude Code and GitHub Copilot to work with semantic models, DAX, TMDL and reports.

• Agent skills
• Data engineering

A config-based command-line tool for running and comparing LLM fine-tuning experiments, controlling prompts, models, optimization strategy and testing from a single YAML file.

• Models

A self-hosted inference server for LLMs, vision-language models and image generation on Apple Silicon, exposing OpenAI, Anthropic and Ollama compatible HTTP APIs with no third-party API keys required.

• Inference

A runtime for agent applications with sandboxed tool execution, streaming Agent-as-a-Service APIs, and deployment locally, on Kubernetes or serverless, now folded into AgentScope 2.0.

• Agent frameworks

A SQL-based framework for querying, provisioning and operating cloud, SaaS, API and MCP resources, usable by both people and AI agents.

• APIs
• Hosting

A Docker container management tool with one-click image updates and container lifecycle controls, working across platforms.

• Containers

A knowledge-base-first agent platform, built around persistent threads, resumable runs and immutable document versions, that provides RAG, human-in-the-loop review and audited skill and tool execution.

• Agent frameworks
• RAG