Havuz

Project Tapestry aims to give every nation and participant frontier AI they can call their own — uniting a global consortium to train a shar

梨园 Liyuan — 以 rp agent为主体的ai角色扮演应用

AI-enabled Intelligent Document Processing for Python: 12+ LLM backends, Pydantic schemas, self-hosted OCR (Nanonets-OCR2-3B), auto-schema d

AI assistant in Telegram that remembers everything and helps you run your life. Self-hosted in one command.

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite fi

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

基于 DeepSeek Harness（DSH）的稳定桌面端，集成Git、内置浏览器与记忆功能 | DeepSeek Harness desktop GUI with local workspaces, Git, browser and memory.

An edge-native Multimodal Android Agent that integrates multimodal perception, memory and action

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluatio

🧬 Symbio（共生）- AI Infra 级多 Agent 协同框架 | 33 Killer Features: 动态 DAG, 本体化记忆, 防过早完成, 数据飞轮, 神经符号安全, OpenTelemetry 可观测, HITL 人类介入, MCP 原生支持, 语义缓存,

One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.

Custom APRL machine-learning algorithm + a curated ML knowledge base of 923 papers, lectures, and explainers. NumPy classifier/regressor, te

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,

Jev-Mem: System-One Controlled Agentic Memory

繁體中文（台灣）個人資料去識別化工具，讓業務文件可以安全地送進 AI 處理 / Reversible Traditional-Chinese (Taiwan) PII de-identification for LLM workflows — fully local

Everything that *went* wrong with Claude.

Private AI on premise

A decision brain for agentic systems: perceive context, compare options, and control execution.

Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.

MCP server for the complete Zabbix API - 237 tools, multi-server, OAuth 2.1 + bearer auth, PDF reports, systemd ready. Works with ChatGPT, C

To know what models don't say out loud.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers

Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats

An all-in-one PDF and Office document platform: self-hosted, open source, under your control. 整合式 PDF / Office 文件處理平台，自架、開源、可控。

Two AI VTubers co-hosting one live show — the realtime engine & orchestration. Open-core, battle-tested by a daily stream.

Learn from your vibe coding instead of just clicking Accept. AhaDiff turns each AI diff into a code-verified lesson, quiz, and review. · 别再无

Maintainer-governed agent for evidence-backed open-source contribution proposals

Unified LLM access layer in Rust — one API for 325 AI providers. 统一 LLM 服务接入层：一套 API 接入 325 家 AI 服务商。

Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud,

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP ex

Evidence-backed AI industry intelligence — trends, source updates, daily data refreshes, and weekly decision briefs.

Local-first MCP gateway. Set up MCP servers once and use them in every AI client, with secrets in the OS keychain, tool integrity checks and

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs

Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI appli

Parallel ai-agent sessions in one panel, with permission-aware tools, preflight conflict checks.

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex

Transformer architecture explained step by step - the full architecture, every attention variant, positional embeddings, and every layer ins

Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi, Hermes). Up to 95% bash compr

Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.

Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.