Bittensor subnet news
Subnet blogs, ecosystem press and community — GitHub lives in its own tab
118SN118Blog · 5d ago
Subnet Summer AMA X SN118 Ditto V2 - YouTube
Subnet Summer AMA X SN118 Ditto V2 YouTube
SN118 Ditto — Google News
118SN118Blog · Jul 24, 2026
Agents need organised memory (Open Source Claude Cowork) Ditto SN118
This week on Novelty Search, the team behind Subnet 118 – Ditto joins to explain how long-term AI memory can become decentralized infrastructure on Bittensor. Ditto is building a persistent memory system for AI agents. Instead of relying only on a model’s context window, Ditto continuously stores, organizes, links, retrieves and refines knowledge over time, allowing agents to build lasting understanding across projects, conversations and workflows. The discussion explores why memory is becoming one of the most important components of agentic AI, how Ditto organizes information into evolving knowledge graphs, why benchmarks for long-term memory matter, how Ditto Bench incentivizes better memory systems through Bittensor, and how fast decentralized inference could enable swarms of AI agents working together in real time. Links Ditto Website: https://heyditto.ai/ Ditto GitHub: https://github.com/heyditto Subnet 118 GitHub: https://github.com/heyditto/sn118 Ditto X: https://x.com/heydittoai Bittensor: https://bittensor.com Novelty Search Playlist: https://www.youtube.com/@OpenTensorFoundation 00:00 Introduction 00:03 Security updates & Polkadot Vault signing 09:59 Introducing Ditto (Subnet 118) 12:36 Why AI needs long-term memory 19:43 MCP integration and developer workflows 24:55 Memory search, vaults & knowledge retrieval 29:53 Building evolving knowledge graphs 34:47 Ditto Bench and benchmarking AI memory 39:53 How modern AI memory systems are evolving 44:49 Incentivizing better memory on Bittensor 49:52 API design and authentication 54:56 Multi-agent orchestration and persistent memory 59:54 Fast decentralized inference on Bittensor 01:05:00 Future roadmap for Ditto 01:10:14 Outro
Opentensor YouTube
118SN118Blog · Jul 3, 2026
Put Your AI on Autopilot: Automations, Recipes, and Code Mode
Ditto can now do work while you're not in the chat. Automations run jobs on a schedule, Recipes chain multi-step flows, and Code Mode gives scripts direct access to every tool you've connected — all created in plain language, all gated by your approval.
SN118 Ditto blog
118SN118Blog · Jun 30, 2026
From Bayes to Your Agents: A Short History of Machine Learning
Machine learning went from probability theory to perceptrons, deep learning, and ChatGPT. Here's the brief history every AI user should know, and why persistent memory, not a bigger model, is the next chapter Ditto is building toward v2.
SN118 Ditto blog
118SN118Blog · Jun 17, 2026
Open-Sourcing the Ditto Harness — and a DittoBench Miner Starter Kit
We rewrote Ditto's agent + memory harness in Rust, open-sourced it under AGPL-3.0 (with a commercial license for partners), and built a self-contained starter kit so anyone can run the agent, practice memory retrieval, and prepare to mine on DittoBench (Bittensor SN118). A heads-up: this harness isn't in Ditto's production path yet — we're migrating to it by end of month, alongside the on-chain mining launch.
SN118 Ditto blog
118SN118Blog · Jun 16, 2026
DittoBench: Clocking Tool-Calling, Memory, and Speed in Any Agent Harness
A benchmark for any agentic harness that wields tools and memory — not just SWE. DittoBench clocks 10 models on whether they call the right tool, find the right memory, and how fast they do both, with a composite speed score that puts latency on the same footing as quality.
SN118 Ditto blog
118SN118Blog · May 19, 2026
An Agent's Nightmares Are the Key to Its Dreams
Nobody fully understands why we dream. One theory is memory consolidation - your brain replaying the day and weaving it into what you already know. We built the algorithmic version of that for Ditto. The bugs we shipped along the way? Those were the nightmares.
SN118 Ditto blog
118SN118Blog · May 14, 2026
Doubling Memory Recall by Extending Ditto's Ranker
We rebuilt the model that decides which past memories Ditto shows the AI. It now considers seven signals instead of three, looks at seventeen hints about your situation instead of six, and was trained directly on the ranking task — roughly doubling how often it surfaces the right memory.
SN118 Ditto blog
118SN118Blog · May 10, 2026
AI for Data Scientists and Analysts: How Persistent Memory Tracks Every Experiment, Dataset, and Insight
Data scientists juggle experiments, datasets, feature pipelines, and model iterations across weeks-long projects — but their AI forgets every hypothesis between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a research partner that knows your entire analytical context.
SN118 Ditto blog
118SN118Blog · May 9, 2026
AI for Product Managers: How Persistent Memory Tracks Every Decision, Roadmap, and User Insight
Product managers juggle roadmaps, user feedback, stakeholder alignment, and competitive intelligence across dozens of features — but their AI forgets every strategic decision between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a product partner that knows your entire product context.
SN118 Ditto blog
118SN118Blog · May 7, 2026
AI for Real Estate Agents: How Persistent Memory Tracks Every Listing, Client, and Deal
Real estate agents manage dozens of clients, hundreds of showings, and thousands of property details simultaneously — but their AI forgets every client preference between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a real estate partner that knows your entire book of business.
SN118 Ditto blog
118SN118Blog · May 6, 2026
AI for HR Professionals and Recruiters: How Persistent Memory Tracks Every Candidate, Role, and Hiring Decision
Recruiters and HR teams juggle dozens of open roles, hundreds of candidates, and endless interview notes — but their AI forgets every candidate between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into an HR partner that knows your entire talent pipeline.
SN118 Ditto blog
118SN118Blog · May 3, 2026
AI for Lawyers: How Persistent Memory Tracks Every Case, Client, and Precedent
Lawyers juggle dozens of active matters — statutes, deadlines, client instructions, opposing counsel's arguments — but their AI forgets it all between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a legal assistant that knows your entire caseload.
SN118 Ditto blog
118SN118Blog · May 2, 2026
AI for Therapists and Counselors: How Persistent Memory Supports Every Session
Therapists and counselors carry rich context about every client — breakthroughs, setbacks, recurring themes, treatment goals — but their AI forgets it all between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a clinical support tool that knows your caseload.
SN118 Ditto blog
118SN118Blog · May 1, 2026
AI for Students: How Persistent Memory Helps You Ace Every Semester
Students juggle five courses, dozens of deadlines, and hundreds of concepts per semester, but their AI forgets everything between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a study partner that actually knows your coursework.
SN118 Ditto blog
118SN118Blog · Apr 30, 2026
AI for Sales Professionals: How Persistent Memory Closes More Deals
Sales reps juggle dozens of active deals, each with unique stakeholders, objections, and timelines — but their AI forgets every prospect between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a sales partner that knows your pipeline as well as you do.
SN118 Ditto blog
118SN118Blog · Apr 29, 2026
AI for Designers: How Persistent Memory Keeps Every Project on Brand
Designers juggle brand guidelines, client feedback, design systems, and multi-project workflows — but their AI forgets everything between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a design partner that knows your aesthetic, your clients, and your process.
SN118 Ditto blog
118SN118Blog · Apr 28, 2026
AI for Marketers: How Persistent Memory Powers Every Campaign, Channel, and Client
Marketers juggle campaigns, audiences, brand voices, and analytics across dozens of channels, but their AI forgets everything between sessions. Here's how persistent memory, threads, and a knowledge graph turn AI into a marketing partner that knows your brand as well as you do.
SN118 Ditto blog
118SN118Blog · Apr 26, 2026
AI for Small Business Owners: How Persistent Memory Runs Your Whole Operation
Small business owners juggle customers, vendors, inventory, marketing, and bookkeeping, but their AI forgets everything between sessions. Here's how persistent memory, threads, and a personal knowledge graph turn AI into an operations partner that knows your business as well as you do.
SN118 Ditto blog
118SN118Blog · Apr 24, 2026
AI for Parents: How Persistent Memory Keeps Track of Your Whole Family
Parents juggle schedules, allergies, school events, and milestones for every kid, but their AI forgets it all between sessions. Here's how persistent memory, threads, and a personal knowledge graph turn AI into a family assistant that actually knows your family.
SN118 Ditto blog
118SN118Blog · Apr 23, 2026
AI for Teachers: How Persistent Memory Remembers Every Student, Lesson, and Breakthrough
Teachers manage hundreds of students, adapt lessons on the fly, and track progress across entire school years, but their AI forgets everything between sessions. Here's how persistent memory, threads, and a personal knowledge graph turn AI into a teaching partner that never loses context.
SN118 Ditto blog
118SN118Blog · Apr 22, 2026
AI for Project Managers: How Persistent Memory Tracks Every Decision, Deadline, and Dependency
Project managers juggle dozens of decisions, stakeholder conversations, and shifting timelines across multiple projects, and their AI forgets all of it between sessions. Here's how persistent memory, threads, and a personal knowledge graph turn AI into a project partner that never loses context.
SN118 Ditto blog
118SN118Blog · Apr 20, 2026
AI for Coaches and Consultants: How Persistent Memory Tracks Every Client Session, Goal, and Breakthrough
Coaches and consultants manage dozens of client relationships, each with unique goals, history, and progress, but AI forgets everything between sessions. Here's how persistent memory, dedicated threads, and a personal knowledge graph turn AI into a practice partner that never loses a client's thread.
SN118 Ditto blog
118SN118Blog · Apr 19, 2026
AI for Developers: How Persistent Memory Tracks Every Project, Decision, and Debug Session
Developers juggle multiple codebases, architectural decisions, and debugging threads, but AI forgets everything between sessions. Here's how persistent memory, dedicated threads, and a personal knowledge graph turn AI into a pair programmer that actually remembers your stack.
SN118 Ditto blog
118SN118Blog · Apr 16, 2026
AI for Job Seekers: How Persistent Memory Turns Your Job Search Into a System
You're tailoring resumes, prepping for interviews, and tracking dozens of applications, but your AI forgets everything between sessions. Here's how persistent memory, dedicated threads, and a personal knowledge graph turn AI into a career partner that knows your story.
SN118 Ditto blog
118SN118Blog · Apr 14, 2026
AI for Content Creators: How Persistent Memory Keeps Your Brand Voice, Ideas, and Strategy in Sync
Content creators juggle brand voice across platforms, recycle ideas without realizing it, and lose brilliant angles in throwaway AI chats. Here's how persistent memory, dedicated threads, and a personal knowledge graph turn AI into a creative partner that actually knows your content.
SN118 Ditto blog