Archives
- 23 Sep mini-AGI's forgetting fix is measured on reading, not on chat
- 23 Sep GameDevBench's 68.8% top score is the only strictly confined row
- 22 Sep Context Engineering Is the Missing Layer Between Your Agent and Its Memory
- 20 Sep Jev shrinks the browser-agent decision loop for faster actions
- 20 Sep The Sealed Lighthouse Passed 52 Checks Without Proving Fun
- 20 Sep MEX on macOS Broke Before Project Memory Even Loaded
- 18 Sep open-code-review protects Octave only if you type a space
- 18 Sep Orca's privacy page survives 82 of its 83 telemetry events
- 17 Sep Moli's efficiency map blends two runs its own bench keeps apart
- 17 Sep CodeBurn's $15 hard cap denies tools when it could stop Claude
- 17 Sep OpenOcta's LICENSE is GPL-3.0 again, its README says Apache-2.0
- 17 Sep AIO Sandbox Asks Docker to Drop Seccomp Before It Sandboxes
- 16 Sep LLM Space guards plugin settings with 0600 but not its API keys
- 16 Sep OpenConnector Declares Its Own Defaults Out of Scope
- 15 Sep MCP for Unity Ships a Drift Check No Workflow Ever Runs
- 14 Sep SoL-Pi's Capability Floor Is Per Mechanism, Not Per Harness
- 13 Sep TradingAgents and LibreChat Are Not Drop-In Replacements
- 13 Sep ripwire Guards Its Gate Count in Source, Not in the PDF
- 13 Sep Gensee Crate's Defense Rate Is the One Number You Cannot Recount
- 12 Sep MetaHarness Advertises Witness Signing Its Bridges Never Export
- 11 Sep HyperFrames Measures 'Same Video' in Decibels, Not Bytes
- 10 Sep SkillHub's Security Scanner Blocks on Crash, Not on Verdict
- 09 Sep CAO's Honest Trust Boundary and Its Phantom Auth Switch
- 08 Sep Ouroboros Preaches Agency and Ships Owner-First Custody
- 07 Sep Open Science's Provenance Engine Would Reject Its Own #1 Badge
- 06 Sep Apache Maka Tracks Its Agents' Screenshots and Ships None of Them
- 05 Sep OpenHarness Lets Its Allow List Outrank Your Deny Rules
- 05 Sep diagram-design Hash-Locks Its Screenshots, Not Its Storefront
- 04 Sep ECC Retired Six MCP Servers Over a Tax Its Catalog Still Pays
- 03 Sep SIE's Public Repo Is an Export Surface, Not a Workshop
- 02 Sep mjlab Source Audit: The Green Badge Proves the CPU Path
- 31 Aug OpenMAIC Source Audit: The Agent Classroom Ships Pedagogy as Machine-Checked Constraint Files
- 31 Aug Archify Source Audit: The Viral Diagram Skill Is Really a Distrust Stack
- 30 Aug God's Eye View: The Viral Globe Is the Demo. The Boundaries Are the Product
- 29 Aug MiniMax H3 LoRAs Are Not a Folder: A 19-Release Compatibility Audit
- 26 Aug Four Viral UI Effects, Audited: What the Demos Do Not Tell You
- 26 Aug After Seedance 2.0, I Re-Audited Four AI Drama Stacks. The Shortlist Was Wrong
- 26 Aug CozyClay: AI Video Needed a Shot Contract, Not Another Prompt Box
- 25 Aug Metal Cannot Preempt: What oMLX Rediscovers From Game Engines
- 24 Aug SQLite in Games: A Save File Is Never Just a File
- 23 Aug MoneyPrinterTurbo: The AI Video Product Is a Production Control Plane
- 23 Aug LongCat-Video: The Continuation State Is the Product
- 22 Aug FreeToken: 284B on a Gaming Desktop, 753B on One Workstation GPU - and the Ratio That Makes It Work
- 21 Aug The New MCP Roadmap - Reading the Protocol's Five Bets on Agentic Infrastructure
- 20 Aug Twelve Concepts, One Missing Layer: What a 12-Link Agent Curriculum Taught Me About Durable Execution
- 20 Aug One Memory Setup, Every Harness: Reading Omnigent's Hindsight Bridge at the Seam
- 20 Aug Ouroboros: The Agent OS That Hides the Answer Key From Its Own Workers
- 17 Aug Superlog: When Your Telemetry Stack Starts Investigating Incidents For You
- 16 Aug Atomic Agent + Unity CLI: Automating Game Builds Without Touching the Editor
- 15 Aug DeepSeek Harness: What If the Agent Loop Itself Were Just Another Plugin?
- 15 Aug Docbank: What If Your Agents Needed a Filing Cabinet, Not a Cloud Drive?
- 21 Jul Unity CLI: From Editor Installs to Verifiable Game-Production Workflows
- 09 Jul Fable 5 Isn't a Faster Chat Model — It's the Substrate for Self-Improving Agent Systems
- 29 Jun The jeo Ecosystem: State Over History — Five Repos That Build Agents Which Don't Forget What Matters
- 25 Jun The Vault That Rewrites Itself: An AI-First Second Brain for Game Teams
- 24 Jun Loops: What Every AI Engineer Needs to Know in 2026
- 24 Jun Claude Code vs. Cursor vs. Codex vs. Antigravity — Six Months of Convergence, and Why the Harness Won
- 22 Jun jeo-code Puts Skills and Approval Gates Around Coding Agents
- 22 Jun Diffusion Models, Visually: How Noise Becomes an Image (and Why a Game Studio Should Care)
- 16 Jun From RAG to Context Layer: What Genie Ontology, LLM Wiki Memory, and HyGRAG Tell Us About the Next Stack
- 18 May Supertonic 3: What On-Device TTS Starts to Look Like When ONNX Is the Contract
- 18 May Antigravity CLI Migration: A Production-Minded agy Checklist After Gemini CLI
- 15 Apr SuperGemma4: A Faster, Sharper Gemma 4 for Local Agent Workloads
- 11 Apr Multimodal Sentence Transformers: A Practical Upgrade for Retrieval Systems
- 10 Apr Feynman: An Open-Source AI Research Agent That Actually Thinks Beyond Search
- 07 Apr AutoBE vs. Claude Code: Verification Beats Raw Agent Flexibility on Big Backend Builds
- 05 Apr LLM Wiki: Why Your Best Knowledge Base May Be an Agent-Maintained Wiki, Not Another RAG Stack
- 03 Apr Claw Dev: One Terminal Coding Agent, Multiple Model Backends
- 02 Apr Why AI Coding Agents Fail — and Why the Harness Matters More Than the Model
- 02 Apr Qwen3.6-Plus Review: 1M Context, Agentic Coding, and Practical AI Agents
- 02 Apr PrismML 1-bit Bonsai: Why 1-Bit LLMs Could Make On-Device AI Actually Practical
- 31 Mar How Claude Code Actually Works: Agentic Loop, Tooling Model, and Operational Guardrails
- 18 Mar Deploy Safer OpenClaw Agents with NVIDIA NemoClaw: A Practical Guide (10:00 AM Edition)
- 17 Mar Designing AI Agent Teams with Codex Subagents: A Practical Guide to Multi-Agent Workflows
- 16 Mar Deploying NanoClaw in Docker Sandboxes: A Practical Security-First Guide
- 18 Feb Harness Engineering: The Layer That Actually Makes Agents Work
- 20 Jan Prompt Repetition: A Simple Trick That Improves LLM Accuracy by 67% (With Zero Latency Cost)
- 18 Jan GLM-4.7 - Your New Coding Partner with 358B Parameters
- 17 Jan OpenContext - Give Your AI Assistant a Persistent Memory for Multi-Agent Workflows