New

A language model trained from scratch and running offline on an ESP32-S3 with a touchscreen chat interface.

Bulk-create AgentScope Platform accounts, auto-mint a Model API key for each, and register them all into 9Router. Zero dependencies, HTTP/SOCKS5 proxy + CDP browser trans

Pi extension that keeps supported provider prompt caches warm during long idle gaps

MCP server exposing Vectros hybrid search, structured records, and RAG/document-ask to MCP-aware desktop agents (Claude Desktop, Cursor, Code, Cline, Continue, VS Code).

GEO 医生：一句话装进 AI 助手，查清豆包、DeepSeek、ChatGPT、Claude 为什么不推荐你，改资料、写内容、再复查。开源中英双语 GEO（生成式引擎优化）skill。

A calm, visual view of the true state of your AI-assisted work. Tracks work items from Asked to Verified on evidence, not agent claims, across Claude Code, Codex, git and

Official TypeScript SDK for SIE (Search Inference Engine)

SIE embeddings integration for LangChain.js

SIE embedding function and reranker for LanceDB

SIE embedding function for ChromaDB

SIE embeddings integration for LlamaIndex.TS

AI agent CLI ringan bergaya Hermes: chat + memory persisten + skill system pluggable (agent bisa bikin skill sendiri) + generator frontend berbasis template. Multi-provid

Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, and Codex. Routes across Ollama, AWS Bedrock, OpenRouter, Databricks, Azure OpenAI, llama.cpp, and

LlamaIndex.TS reader and node parser for Xberg — extract text, tables, metadata, and structure-aware nodes from 107 document formats with optional OCR.

LangChain.js document loader for Xberg — extract text, tables, and metadata from 107 document formats with optional OCR.

The deterministic agent-integrity gate. One ruleset, evaluated on the actual diff/commands as a verdict, enforced everywhere a change can be made.

Model Context Protocol server for Rollbar

Sandboxed JavaScript REPL for deepagents using QuickJS (WASM)

One strict way to run a software project with any AI coding agent: issues as specs, handoff prompts, audits that catch every problem down to a typo, and fixes for what th

Universal, local-first, persistent memory layer for AI agents, LLM apps, and chatbots.

Local Anthropic Messages, streaming and tool-use workflows. Replies use configured scenarios or labeled deterministic stubs; no model runs.

Framework-agnostic embeddable AI chat widget. One call mounts a streaming chat bubble into any page — no React, no framework, themeable.

Record & replay LLM API calls in tests. Zero tokens, millisecond runs, deterministic CI.

A typechecker for your issue tracker — every checked acceptance criterion must cite a real commit and proof, verified by `ztrack check` (and enforced on coding agents via

You create the instructions; Sanity AI Assist does the rest.

🔒 Your private AI assistant, 100% local on Windows: chat, vision, documents (RAG), web search, images, videos with sound, voice, code projects, MCP tools — one-line inst

LangChain.js / LangGraph tool: agents fetch x402 APIs while an owner-signed, on-chain budget decides every payment

CLI tool for Genspark Tool API - search, crawl, analyze images, generate media

LightRAG knowledge-graph retrieval middleware for tagma-sdk pipelines

CommHub Server — AI Agent communication hub with MCP protocol, multi-network isolation, user auth, and MCP tools (17 collaboration-core + node/provider ops tools; authori

CogmemAi is the safe, persistent memory that keeps Ai in line. It remembers what matters across every session, stops any action that breaks the rules you set before it ha

One open-source modeler for structures, heat and fluids, built from scratch in pure Rust: parametric part in, verified results out. Automatic all-hex and tet meshing, our

Multi-account proxy for Claude Code and Codex: pools Claude Max, ChatGPT/Codex, API-key and third-party backend accounts, and rotates on quota

Loosely parse a string as JSON with numerous affordances for syntax errors

Creative vertical video editing skill for AI agents (Claude Code, Codex, OpenCode, Cursor, Hermes): named styles, creative mode, HyperFrames + voice-first mix.

akm (Agent Knowledge Manager) — a portable, local-first capability library for AI agents. Discover, load, share, and improve reusable skills, scripts, workflows, and know

Illustrated comic-style cheat sheets for ML, LLMs, AI safety, LeetCode and Git, plus a SwiftUI study app (Panels) to read them and quiz yourself.

Cromford: the open-source software factory. Tickets in, reviewed, merged and production-checked changes out.

An Antora extension to generate llm.txt files for LLM consumption.

Anthropic adapter for Zhivex AI SDK.