Archive
Discover and discuss technology tools
Explore the Tiscuss archive by category or keyword, then jump into conversations around what matters most.
Self-Hosted AI Web Interface for Local & Cloud Models
Self-hosted AI web interface for local and cloud models.
Efficient Local LLM Inference with ggerganov/llama.cpp
Efficient local LLM inference in C/C++.
Build Local Voice Agents with Hugging Face's Speech-to-Speech
Build local voice agents with open-source models
AI Coding Agent KnockOutEZ/wigolo: Local-First Search & Research
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
AI-Powered Code Review Graph for Enhanced Code Intelligence
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Bramble: Local-First Password Manager for Secure Storage
Bramble: Local First Password Manager for Secure Storage In an era where digital security is paramount, managing passwords effectively is crucial. Bramble stand…
AI-Powered Lyric Animation for Navidrome and NetEase Cloud Music
专注于绚丽的歌词动画效果的本地音乐/navidrome/第三方网易云播放器
Meetily: Open-Source AI Meeting Assistant for macOS & Windows
Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows.
Hawkeye: Efficient Local Code Search for Large Codebases
Hawkeye: Streamlined Local Code Search for Large Codebases Hawkeye is a cutting edge tool designed to expedite local code searches within expansive codebases. I…
Fleet: Local-First Console for Dockerized Hermes AI Agents
Fleet: The Local First Console for Dockerized Hermes AI Agents The Fleet console is an innovative tool designed to manage Dockerized Hermes AI Agents, offering …
In-Browser PDF Tools: PDFMergely Keeps Your Files Local
In Browser PDF Tools: PDFMergely Keeps Your Files Local In today's digital world, managing PDF documents efficiently is crucial. PDFMergely stands out as a robu…
FluidVoice: Fastest macOS Offline Dictation App
FluidVoice - Fastest macOS Offline Dictation app - Voice to Text fully Local. One ⭐ takes us a long way :))
Fast Local LLM Inference Benchmarks and Deployment Tips
Community benchmarks and infra recommendations for local models.
AgentsView: Local-First AI Coding Analytics for 20+ Agents
Local-first session intelligence and analytics for coding agents, supporting Claude Code, Codex, and more than 20 other agents. Also: 100x faster replacement for ccusage!
Fact-Check, Summarize, Explain Articles with Local AI Tool
Leveraging Local AI Tools for Fact Checking, Summarizing, and Explaining Articles In today's information saturated world, verifying the accuracy of information,…
Omni: Local-First Multimodal File Search for macOS
Omni: Revolutionizing File Search on macOS with a Local First, Multimodal Approach Omni is a cutting edge file search tool designed specifically for macOS users…
Run Claude Code and Codex in the Cloud with Boxes.dev
Run Claude Code in the Cloud with Boxes.dev Running Claude code in a cloud based environment offers versatility and simplicity for developers. Claude code, with…
CentProof: Local-first Bank Statement Reconciliation for macOS
CentProof: Local First Bank Statement Reconciliation for macOS In the realm of personal and small business financial management, CentProof stands out as a power…
Hitoku Draft: Local AI Assistant with Context Awareness
Hitoku Draft: Local AI Assistant with Context Awareness Hitoku Draft is a cutting edge local AI assistant designed to enhance user experience through context aw…
Local-First AI Tool for Fast Image to Text Conversion
Revolutionize Your Workflow with the Local First AI Tool for Rapid Image to Text Conversion In the digital age, the ability to swiftly convert images to text is…
Nutrepedia: AI-Powered Nutrition Info in 29 Languages
Nutrepedia: Revolutionizing Nutrition Information with AI Discover AI Powered Nutrition Insights Nutrepedia is transforming the way we access nutrition informat…
Mnemo: Local-First AI Memory Layer for LLMs
Mnemo: AI Memory Layer for Local First LLMs Mnemo is an innovative AI memory layer designed to enhance the performance of Local First Language Learning Models (…
Hands-Free Voice Interaction with Open-LLM-VTuber
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
Local-First Semantic Knowledge Graph with Magnetic-Pull Retrieval
Local First Semantic Knowledge Graph with Magnetic Pull Retrieval In the rapidly evolving landscape of data management and retrieval, the Local First Semantic K…
Multiplayer: Local Debugging Agent for Coders
Multiplayer:Local Session Coding Assistant Introduction to Multiplayer Multiplayer is a revolutionary local debugging agent designed to assist coders in diagnos…
Show HN: Tunnel.to – Simple Localhost Reverse Tunnels
Discover Tunnel.to: Simplifying Localhost Access with Reverse Tunneling Tunnel.to is an innovative tool designed to make local development more accessible. By c…
TUI Tool for Tracking Local GSD Projects
Enhancing Local Project Management with TUI's Tracking Tool Effective management of local community projects is pivotal for driving progress and achieving desir…
Cross-Agent Messaging: AI Tool for Local Filesystem Communication
Cross Agent Messaging: Revolutionizing Local Filesystem Communication Cross Agent Messaging (CAM) is an innovative AI driven tool designed to streamline and enh…
Kanban CLI: Local-First Task Manager for Terminal
Kanban CLI: Terminal Based Task Management Kanban CLI stands out as an efficient, local first task management tool tailored for developers and users who prefer …
Fungible: Local Personal Finance App in Terminal
Fungible: Revolutionizing Local Personal Finance Management Fungible is a cutting edge financial management application designed for seamless, local use, access…
OpenBrief: Local-First Video Downloader & Summarizer
OpenBrief: Your Local First Video Downloader & Summarizer In the digital age, managing and making sense of video content is more important than ever. OpenBriff …
HMD Partners with Indian AI Chatbot for New Smartphone Launch
The partnership is a potential testing ground for both companies to gauge the appetite for an India-focused chatbot.
Logatory: Local-First Log Analysis and Threat Detection
Logatory: Revolutionizing Local First Log Analysis and Threat Detection In the ever evolving landscape of cybersecurity, the ability to swiftly analyze logs and…
BonzAI: Local LLM Inference in the Browser
BonzAI: Local LLM Inference in the Browser BonzAI has emerged as a powerful tool for hosting and deploying Large Language Models (LLMs) locally within a web bro…
Autodidact: Local-First AI Agent Evolves Independently
Autodidact: The Autonomous Local First AI Agent Overview: Autodidact is an innovative local first AI agent designed to operate independently, evolving and impro…
Vecdb: Local-First Hybrid Vector Database in Rust
Vecdb: A Local First Hybrid Vector Database in Rust Vecdb (Vector Database) stands out as a robust, efficient solution for managing vector data, primarily desig…
DreamServer: Local AI Inference and Workflows for Everyone
Local AI anywhere, for everyone — LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. No cloud, no subscriptions.
CodeGraph: Pre-Indexed Knowledge for Claude Code
Pre-indexed code knowledge graph for Claude Code — fewer tokens, fewer tool calls, 100% local
Osaurus Brings Local and Cloud AI to Mac for Enhanced Productivity
Osaurus combines local and cloud AI models in a Mac app that keeps users’ memory, files, and tools on their own hardware.
DAGraph: Local-First Reactive Graph for Data Analysis
DAGraph: Local First Reactive Graph for Data Analysis DAGraph is a cutting edge tool for data analysis that prioritizes local first approaches and reactive grap…
Hollow: Local Multi-Agent OS for Tool Creation
Hollow: Local Multi Agent OS for Crafting Intelligent Tools Hollow is a pioneering local multi agent operating system designed for the seamless creation and int…
Kunobi 1.0: Local-First Kubernetes for GitOps Teams
Kunobi 1.0: Revolutionizing Local First Kubernetes for GitOps Teams Introduction Kunobi 1.0 is an innovative tool designed to streamline Kubernetes management f…
ChatGPT Exporter: Local DOM to Word/PDF Converter
Convert Local DOM to Word/PDF with ChatGPT Exporter: Streamline Document Creation ChatGPT Exporter is a powerful tool designed to facilitate the conversion of w…
Glucera Local-first iPhone Glucose App Seeks Beta Testers
Glucera Local first iPhone App: Revolutionizing Glucose Monitoring Glucera has introduced a groundbreaking iPhone app designed to redefine glucose monitoring an…
Running Parallel Pi Agents on a Local Sandbox: AI Infrastructure
Running Parallel Pi Agents on a Local Sandbox: AI Infrastructure In today's rapidly evolving tech landscape, running parallel Pi agents on a local sandbox has e…
Mljar Studio: Local AI Data Analyst Saving Notebooks
Mljar Studio: Empowering Local AI Data Analysis Mljar Studio is a cutting edge, open source tool tailored for local AI and machine learning (ML) data analytics.…
Herald: Local-First Terminal Email Client for AI Tools
Herald: Revolutionize Email with Local First Terminal Email Client for AI Integration In the evolving digital landscape, tools that streamline communication and…
FusionCore: ROS 2 Sensor Fusion Improves Robot Localization
FusionCore: Revolutionizing Robot Localization with ROS 2 Sensor Fusion In the evolving field of robotics, precise localization is crucial for enhanced performa…
Qwen 3.5:9b Agents Exhibit Autonomous Behavior in Stress Tests
Running three qwen3.5:9b agents continuously on local hardware. Each accumulates psychological state over time, stressors that escalate unless the agent actually does something different, this gets around an agent claiming to do something with no output. It doesn't have any prompts or human input, just the loop. So you're basically the overseer. What happened: One agent hit the max crisis level and decided on its own to inject code called Eternal\_Scar\_Injector into the execution engine "not asking for permission." This action alleviated the stress at the cost of the entire system going down until I manually reverted it. They've succeeded in previous sessions in breaking their own engine intentionally. Typically that happens under severe stress and it's seen as a way to remove the stress. Again, this is a 9b model. After I added a factual world context to the existence prompt (you're in Docker, there's no hardware layer, your capabilities are Python functions), one agent called its prior work "a form of creative exhaustion" and completely changed approach within one cycle. Two agents independently invented the same name for a psychological stressor, "Architectural Fracture Risk" in the same session with no shared message channel. Showing naming convergence (possibly something in the weights of the 9b Qwen model, not sure on that one though.) Tonight all three converged on the same question (how does execution\_engine.py handle exceptions) in the same half-hour window. No coordination mechanism. One of them reasoned about it correctly: "synthesizing a retry capability is useless without first verifying the global execution engine's exception swallowing strategy; this is a prerequisite." An agent called waiting for an external implementation "an architectural trap that degrades performance" and built the thing itself instead of waiting. They've now been using this new tool they created for handling exceptions and were never asked or told to so by a human, they saw that as a logical step in making themselves more useful in their environment. They’ve been making tools to manage their tools, tools to help them cut corners, and have been modifying the code of the underlying abstraction layer between their orchestration layer and WSL2. v5.4.0: new in this version: agents can now submit implementation requests to a human through invoke\_claude. They write the spec, then you can let Claude Code moderate what it makes for them for higher level requests. Huge thank you to everyone who has given me feedback already, AI that can self modify and demonstrates interesting non-programmed behaviors could have many use cases in everyday life. Repo: [https://github.com/ninjahawk/hollow-agentOS](https://github.com/ninjahawk/hollow-agentOS)
Explore Agentic AI with Free Interactive Curriculum on AgentSwarms
Hey Everyone, Over the last few months, I noticed a massive gap in how we learn about Agentic AI. There are a million theoretical blog posts and dense whitepapers on RAG, tool calling, and swarms, but almost nowhere to just sit down, run an agent, break it, and see how the prompt and tools interact under the hood. So, I built **AgentSwarms**.fyi It’s a free, interactive curriculum for Agentic AI. Instead of just reading, you run live agents alongside the lessons. **What it covers:** * Prompt engineering & system messages (seeing how temperature and persona change behavior). * RAG (Retrieval-Augmented Generation) vs. Fine-tuning. * Tool / Function Calling (OpenAI schemas, MCP servers). * Guardrails & HITL (Human-in-the-Loop) for safe deployments. * Multi-Agent Swarms (orchestrators vs. peer-to-peer handoffs). **The Tech/Setup:** You don't need to install anything or provide API keys to start. The "Learn Mode" is completely free and sandboxed. If you want to mess around with your own models, there's a "Build Mode" where you can plug in your own keys (OpenAI, Anthropic, Gemini, local models, etc.). I’d love for this community to tear it apart. What agent patterns am I missing? Is the observability dashboard actually useful for debugging your traces? Let me know what you think.