Archive
Discover and discuss technology tools
Explore the Tiscuss archive by category or keyword, then jump into conversations around what matters most.
AI Tool: mattpocock/skills for Real Engineers
Skills for Real Engineers. Straight from my .claude directory.
Top Codex Skills for Automating Workflows
A curated list of practical Codex skills for automating workflows across the Codex CLI and API.
GitNexus: Client-Side Code Intelligence Engine for GitHub Repos
GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive knowledge graph wit a built in Graph RAG Agent. Perfect for code exploration
Wafaa.io: AI Tool for Secure Digital Contracts in Minutes
Create secure digital contracts in minutes
AI Tool: Bartei's New Release on GitHub
Bartei’s New Release on GitHub: Revolutionizing AI Interaction! Bartei, an advanced open source AI tool, has just been released on GitHub, bringing a new level …
Git-agecrypt: Transparent File-Level Encryption for Git
Git agecrypt: Transparent File Level Encryption for Git Git agecrypt is an innovative tool designed to provide transparent file level encryption for Git reposit…
Garritfra: Revolutionizing AI Tools on GitHub
Garritfra: Revolutionizing AI Tools on GitHub Garritfra is emerging as a key player in the AI technology market, offering a suite of advanced tools accessible v…
Dirac Run: Revolutionizing AI on GitHub
Dirac Run: Revolutionizing AI on GitHub In the rapidly evolving world of artificial intelligence, innovative tools like Dirac Run are making waves. Dirac Run is…
AI Agents: Identity, Not Memory, Was the Key to Stability
Everyone's building memory layers right now. Longer context, better embeddings, persistent state across sessions. I spent weeks on the same thing. But the failure mode that actually cost me the most debugging time had nothing to do with memory. Here's what it looked like: an agent would be technically correct - good reasoning, clean output - but operating from the wrong context entirely. Answering questions nobody asked. Taking actions outside its scope. Not hallucinating. Drifting. Like a competent person who walked into the wrong meeting and started contributing without realizing they're in the wrong room. I run 11 persistent agents locally. Each one is a domain specialist - its entire life is one thing. The mail agent's every session, every test, every bug fix is about routing messages. The standards auditor's whole existence is quality checks. They're not generic workers configured for a task. They've each accumulated dozens of sessions of operational history in their domain, and that history is what makes them good at their job. When they started drifting, my first instinct was what everyone's instinct is: better memory. More context. None of it helped. An agent with perfect recall of its last 50 sessions would still lose track of who it was in session 51. What actually fixed it I separated identity from memory entirely. Three files per agent: passport.json - who you are. Role, purpose, principles. Rarely changes. This is the anchor. local.json - what happened. Rolling session history, key learnings. Capped and trimmed when it fills up. observations.json - what you've noticed about the humans and agents you work with. Concrete stuff like "the git agent needs 2 retries on large diffs" or "quality audits overcorrect on technical claims." The agent writes these itself based on what actually happens. Identity loads first, then memory, then observations. That ordering matters. When the identity file loads first, the agent has a stable reference point before any history lands. The mail routing agent learned the sharpest version of this. When identity was ambiguous, it would route messages from the wrong sender. The fix wasn't better routing logic - it was: fail loud when identity is unclear. Wrong identity is worse than silence. The files alone weren't enough Three JSON files helped, but didn't scale past a few agents. What actually made 11 work is that none of them need to understand the full system. Hooks inject context automatically every session - project rules, branch instructions, current plan. One command reaches any agent. Memory auto-archives when it fills up. Plans keep work focused so agents don't carry their entire history in context. The system learned from failing. The agents communicate through a local email system - they send each other tasks, status updates, bug reports. One agent monitors all logs for errors. When it spots something, it emails the agent who owns that domain and wakes them up to investigate. The agents fix each other. The memory agent iterated three sessions to fix a single rollover boundary condition - each time it shipped, observed a new edge case, and improved. These aren't cold modules. They break, they help each other fix it, they get better. That's how the system got to where it is. You don't need 11 agents The 11 agents in my setup maintain the framework itself. That's the reference implementation. But u could start with one agent on a side project - just identity and memory, pick up where u left off tomorrow. Need a team? Add a backend agent, a frontend agent, a design researcher. Three agents, same pattern, same commands. Or scale to 30 for a bigger system. Each new agent is one command and the same structure. What this doesn't solve This all runs locally on one machine. I don't know whether identity drift looks the same in hosted environments. If u run stateless agents behind an API, the problem might not exist for you. Small project, small community, growing. The pattern itself is small enough to steal - three JSON files and a convention. But the system that keeps agents coherent at scale is where the real work went. pip install aipass and two commands to get a working agent. The .trinity/ directory is the identity layer. Has anyone else tried separating identity from memory in their agent setups? Curious whether the ordering matters in other architectures, or if it's just an artifact of how this system evolved.
Master System Design with AI Tool: donnemartin/system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
DeepSeek-V3: Advanced AI Tool Trends on GitHub
DeepSeek V3: Advanced AI Tool Trends on GitHub DeepSeek V3 is a cutting edge AI tool available on GitHub, designed to push the boundaries of artificial intellig…
TauricResearch TradingAgents: Multi-Agent LLM Financial Trading
TradingAgents: Multi-Agents LLM Financial Trading Framework
Claude Code Templates: CLI Tool for Configuration and Monitoring
CLI tool for configuring and monitoring Claude Code
AI Industry Shifts: The End of All-You-Can-Eat AI Plans?
I am a GitHub Copilot Pro+ user. I have been enjoying 39 dollars plan that actually is worth 60 dollars compute with 1500 premium prompts to models count based. Given the availability of free tier models and model switching option, It has felt like never ending. It will be turned into token based after June. This corresponds to the projections about "the death of the ai buffet" I think. Less bundled memberships, more token based costs. As all these foundational model providers crave for profit, I think this is the natural step we are heading. They need to be able to measure and limit the use for profit. I am just curious how fast that will happen? Should we not take cheap & free AI for granted? Or can open-source models actually create a balance? If we are heading for less accessibility, how should average user be prepared?
Arc Sentry: Advanced Prompt Injection Detector for LLMs
Been working on Arc Sentry, a whitebox prompt injection detector for self-hosted LLMs (Mistral, Llama, Qwen). Most detectors pattern-match on known attack phrases. Arc Sentry watches what the prompt does to the model’s internal representation instead, so it catches indirect, hypothetical, and roleplay-framed attacks that get through keyword filters. Benchmark on indirect/roleplay/technical prompts (40 OOD prompts): • Arc Sentry: Recall 0.80, F1 0.84 • OpenAI Moderation API: Recall 0.75, F1 0.86 • LlamaGuard 3 8B: Recall 0.55, F1 0.71 Arc Sentry has the highest recall — it catches more of the hard cases. Blocks before model.generate() is called. The lightweight pre-filter runs on CPU with no model access. pip install arc-sentry GitHub: https://github.com/9hannahnine-jpg/arc-sentry Happy to answer questions about how it works.
AI Tool Dreeseaw: Revolutionizing GitHub Automation
Revolutionizing GitHub Automation with AI Tool Dreeseaw In the fast paced world of software development, efficiency and automation are paramount. Enter Dreeseaw…
Pawelb0 AI Tool: Revolutionizing GitHub Repositories
Pawelb0 AI Tool: Revolutionizing GitHub Repositories Introduction In the rapidly evolving world of software development, leveraging cutting edge tools can signi…
Light Cloud AI Tools: Revolutionizing Development on GitHub
Light Cloud AI Tools: Revolutionizing Development on GitHub In the fast paced world of software development, staying ahead of the curve is crucial. Light Cloud …
Matzapata AI Tool: Revolutionizing Code on GitHub
Matzapata AI Tool: Revolutionizing Code on GitHub In the fast evolving world of software development, efficiency and accuracy are paramount. Matzapata AI Tool i…
AI Tool for Code Generation: GitHub's Sachitrafa
GitHub's Sachitrafa: Revolutionizing Code Generation with AI In the fast paced world of software development, efficiency and accuracy are paramount. GitHub's Sa…
Drio AI: Revolutionizing Code Generation on GitHub
Drio AI: Revolutionizing Code Generation on GitHub In the fast paced world of software development, efficiency and accuracy are paramount. Drio AI is at the for…
GitHub's Scastiel: AI-Powered Code Analysis Tool
Enhance Your Code with GitHub’s Scastiel: The Ultimate AI Tool for Enhanced Code Analysis In the rapidly evolving landscape of software development, tools that …
OpenClaw: Cross-Platform Personal AI Assistant
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Learn to Code: Recreate Tech with CodeCrafters AI
Master programming by recreating your favorite technologies from scratch.
Top AI-Powered Tools: Explore curl for Data Transfer
A command line tool and library for transferring data with URL syntax, supporting DICT, FILE, FTP, FTPS, GOPHER, GOPHERS, HTTP, HTTPS, IMAP, IMAPS, LDAP, LDAPS, MQTT, MQTTS, POP3, POP3S, RTMP, RTMPS, RTSP, SCP, SFTP, SMB, SMBS, SMTP, SMTPS, TELNET, TFTP, WS and WSS. libcurl offers a myriad of powerful features
AI Memory Upgrade for Coding Agents: Beads on GitHub
Beads - A memory upgrade for your coding agent
GitNexus: Client-Side Code Intelligence for GitHub
GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive knowledge graph wit a built in Graph RAG Agent. Perfect for code exploration
PostHog: AI-Powered Platform for Product Success
🦔 PostHog is an all-in-one developer platform for building successful products. We offer product analytics, web analytics, session replay, error tracking, feature flags, experimentation, surveys, data warehouse, a CDP, and an AI product assistant to help debug your code, ship features faster, and keep all your usage and customer data in one stack.
AI Skills Directory: mattpocock/skills on GitHub
My personal directory of skills, straight from my .claude directory.
Free Claude Code AI: Terminal, VSCode, Discord Integration
Use claude-code for free in the terminal, VSCode extension or via discord like openclaw
Refactoring AI Tools: GitHub's Latest Innovation on Hacker News
Enhance Your Coding Skills with Refactoring HQ on GitHub Refactoring HQ on GitHub is a comprehensive resource designed to help developers improve their coding s…
Build Neurall: Revolutionizing AI Toolkit on GitHub
Build Neural Your Gateway to AI Development Introduction Building neural networks has become more accessible than ever with Build Neural . This powerful platfor…
AI Tool for GitHub Repositories by Russell Romney
GitHub russellromney: A Comprehensive Overview Introduction GitHub is a platform that has revolutionized the way developers collaborate, share, and manage code.…
AI Tool: GitHub's nv404 for Enhanced Coding Efficiency
Streamlining Workflows with GitHub: An In depth Guide to GitHub.com/nv404 GitHub, the globally recognized platform for version control and collaboration, contin…
AI Tool: Vincenzomanto's GitHub Repository
Optimizing Your Workflow with GitHub: The Vincenzomanto Repository Welcome to the Vincenzomanto GitHub repository. In this article, we will explore the power an…
AI Browser Automation Tool: GitHub Browser-Use
Unleashing the Power of Browser Automation with GitHub Repository "browser use" Automating browser tasks can greatly enhance productivity and efficiency. The [G…
AI Agents Maintain Karpathy-Style LLM Wiki in Markdown and Git
Show HN: A Karpathy Style LLM Wiki Your Agents Maintain (Markdown & Git) Introduction Introducing a revolutionary wiki system inspired by Andrej Karpathy's appr…
Agzam AI Tool: Revolutionizing GitHub Projects
agzam: Streamline Your Development Workflow with GitHub's Advanced CLI GitHub's agzam repository offers an advanced command line interface (CLI) tool designed t…
Emacs Tool: Browse GitHub Repos Without Cloning
Show HN: Browse GitHub Repos in Emacs Without Cloning Introducing a new Emacs package that allows you to browse GitHub repositories directly within your Emacs e…
Amal David's GitHub AI Tool: A Comprehensive Guide
Explore amal david.github.io: Your Ultimate Guide What is amal david.github.io? amal david.github.io is a versatile and powerful platform designed to showcase y…
Top Codex Skills for Automating Workflows with CLI and API
A curated list of practical Codex skills for automating workflows across the Codex CLI and API.
AI Hacking Tool Z4nzu Trends on GitHub
ALL IN ONE Hacking Tool For Hackers
AI Tool RefactoringHQ Launched on GitHub
AI Tool RefactoringHQ Launched on GitHub: Revolutionizing Code Optimization RefactoringHQ, an advanced AI driven tool, has just been launched on GitHub, offerin…
AI Tool: Russellromney's GitHub Repository
Exploring Russellromney's GitHub Repository: A Comprehensive Guide to AI Tools Russellromney's GitHub Repository is a treasure trove of cutting edge AI tools an…
AI Tool for Code Generation and Analysis on GitHub
Revolutionize Your Development Workflow with AI Powered Code Generation and Analysis on GitHub In the fast paced world of software development, efficiency and a…
Vincenzo Manto's AI Tool on GitHub: A Game Changer
Vincenzo Manto's AI Tool on GitHub: A Game Changer Vincenzo Manto's AI Tool on GitHub is revolutionizing the way developers, researchers, and enthusiasts approa…
AI Browser Usage Tool Launched on GitHub
AI Browser Usage Tool Launched on GitHub The latest innovation in AI driven analytics has landed on GitHub: a new Browser Usage Tool. This open source project i…
AI-Powered CRM Tool: Nex CRM on GitHub
AI Powered CRM Tool: Nex CRM on GitHub In the fast evolving landscape of customer relationship management (CRM), Nex CRM stands out as a pioneering AI Powered C…
A Karpathy-Style LLM Wiki Maintained by Agents with Markdown and Git
A Karpathy Style LLM Wiki Maintained by Agents with Markdown and Git In the rapidly evolving landscape of artificial intelligence, maintaining a robust and up t…
AI Tool: GitHub's agzam Revolutionizes AI Development
GitHub's Agzam Revolutionizes AI Development GitHub, the leading platform for software development and version control, has introduced a groundbreaking new tool…