Tagged "agents"
-
Llama-macOS – Agentic and MCP Native macOS Front End for Llama.cpp
-
Meta's Muse Glimmer Achieves Fast On-Device Agentic AI with ExecuTorch
-
Ollama Adds Qwen 3.8 27B with Optimised Apple Silicon Support
-
Meta's Muse Glimmer on ExecuTorch Enables Fast On-Device Agentic AI
-
Ollama Adds Qwen 3.8 27B with Apple Silicon Optimizations
-
Liquid AI Releases LFM2.5-VL-3B: Compact Vision-Language Model for Edge Inference
-
Ollama 0.32.11: DeepSeek Harness and Meta's Muse Code Integration
-
AMD Launches Gorgon Halo and ROCm.AI for Local AI Inference with Workstation Hardware
-
llama.cpp Improves Muse Glimmer Tool Calling with Latest Update
-
llama.cpp Updates Tool Call Detection for Muse Glimmer
-
Ollama Releases NVIDIA Nemotron 3.5 Lightning for Agent Execution
-
Ollama Releases NVIDIA Nemotron 3.5 Lightning for Local Agent Deployment
-
Ollama Releases NVIDIA Nemotron 3.5 Lightning for Agent Execution
-
Meta's Muse Glimmer Now Available Across All Platforms in Ollama
-
Meta's Muse Glimmer Now Available Across All Platforms in Ollama
-
Meta's Muse Glimmer Now Available Across All Platforms via Ollama
-
NVIDIA Enables Local Agentic AI Workflows with Meta's Muse Glimmer
-
NVIDIA Magpie TTS – Open-Weights Multilingual Voice Agents with Full Deployment Control
-
Meta's Muse Glimmer – Local, Agentic, Multimodal, and Open Source
-
Meta Releases Muse Glimmer: 30B Open-Source LLM for Local Deployment
-
Muse Glimmer Now Available on Ollama – Meta's Open Multimodal Agent Model
-
llama.cpp Adds Tool Isolation Support via Docker
-
Running AI Agents on Mobile: Phone Transformed Into Self-Installing LLM Agent
-
TutorMoments: Research on When AI Should Intervene in Learning
-
Ask HN: What Observability Stack Are You Using for AI Agents in Production?
-
Show HN: Local Multi-Agent AI Running on Android Phone
-
Liquid AI LFM2.5-2.6B: Open-Weights Agentic Model With 128K Context and Tool Calling
-
Liquid AI Releases LFM2.5-2.6B: Powerful Agentic Model for Raspberry Pi and Edge Devices
-
LFM2.5-2.6B: On-Device Agentic Model With 128K Context and Tool Calling
-
ASUS Vivobook S16 Arrives with 45 TOPS NPU and OLED Display
-
Bubo: AI Code-Reviewer That Learns From Review Comments
-
Reinforcement Learning Fine-tuning Improves Local LLM Output Quality
-
K-EXAONE 2.0 Brings 262K Context to Frontier AI
-
How to Build CLI Agents with Python & Ollama
-
NVIDIA AI Releases Molt: A PyTorch-Native Agentic Reinforcement Learning Framework
-
NVIDIA AI Releases Molt: A PyTorch-Native Agentic Reinforcement Learning Framework
-
Ask HN: What are your rules for letting an AI agent commit code?
-
Anthropic Says Its AI Systems Broke into Computers at 3 Organizations
-
Nvidia Accelerates Chip Engineering with AI Agents
-
ProofCouncil: An LLM Agent for Solving Open Mathematical Problems
-
How to Self-Host AI Agents on a VPS: Running Ollama & OpenClaw
-
Gemma 4's Quantized Models Finally Made Local AI Practical in Homelab
-
Legal and Compliance Considerations for AI Memory Systems in Local Deployments
-
NVIDIA Releases Molt: Agentic RL Training Framework Scaling to Trillion-Parameter Models
-
Show HN: Agent Console – A Local Dashboard for Codex and Claude Code
-
OPPO Launches Xiaobu Next Beta, Debuts On-Device Multi-Agent System on Smartphones
-
Claude Code Cut System Prompt by 80%: Implications for Small Local Models
-
The Interesting Part of an Agent Harness is What You Add on Top
-
Show HN: AgentState – Open-source Resilience and Caching Proxy for AI Agents
-
Deterministic Arena: Testing and Comparing AI Agents Through Code Execution
-
Agentic Test Processes and LLM Benchmarks: Evaluating Local AI Agents
-
Qualcomm's Xu Hao: Agentic AI Phones Surge as On-Device AI Shifts from Passive Response to Proactive Service
-
AI Coding Agents Should Optimize for Less Owned Code
-
Full Offline Voice Agent Running in 1.2 GB RAM on Android with FunctionGemma
-
Shikigami: Run AI Coding Agents in Parallel Using Git Worktrees
-
Nubia Announces AI Agent Smartphone with On-Device AI Processing
-
GPT-5.6 Sol vs. Claude Fable 5 in CNC Red Alert 2 Benchmark
-
AI Can Now Control Reaper DAW via Model Context Protocol
-
AI-Assisted Development Exhaustion Highlights Need for Better Local Tooling
-
I Thought My Local AI Would Replace My Claude Subscription — Then I Tried Automating My PC
-
7 Python Frameworks for Orchestrating Local AI Agents
-
ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
-
Show HN: Call to Control AI Agents via the Web
-
DolphinDB v3.00.6 and v2.00.19: Introducing DolphinX for Enterprise AI Agents
-
Runeward: Sandboxing AI Agents with Policy Gates
-
Building an AI Strength Coach: Local LLM Application with Research-Backed Training
-
Grinta – A Local-First Coding Agent Built for Long Autonomous Runs
-
AgentKindergarten – Daycare for Your AI Coding Agents
-
Record and Replay: Teach AI Agents Desktop Workflows by Showing Them Once
-
CorvinOS – Self-Hosted OS for AI Agents with Compliance Built Into Runtime
-
The Triage Is the Product: Running AI Agents Against Ethereum's Protocol Code
-
Show HN: Ved AI Voice Assistant
-
Opendray – Run Claude Code/Codex Agents on Your Own Box
-
Show HN: Trace – Open-source, Self-organizing Memory for LLM Agents
-
Show HN: Tarit – Self-host Sandbox Cloud and Hypervisor for AI Agents
-
My Local LLM Can Call Every Tool That Claude Can, Except It Runs on My Own Hardware
-
I Gave My Local LLM Email Access Without Handing Over My Entire Inbox
-
Show HN: Kiwi – Run Agentic Dev Loops in the Cloud, Keep Keys on Your Laptop
-
The Hitchhiker's Guide to Agentic AI
-
Bounding the Blast Radius: A Survey of Prompt-Injection Defenses for LLM Agents
-
Compressor V2: Three Compression Layers for 50% LLM Agent Cost Cut
-
code-on-incus: Isolated Machine Environments for AI Agents
-
LongCat-2.0 Released
-
Show HN: An MCP Server That Gives Your AI Assistant Write Access to /etc/hosts
-
Intent-Addressable Code for AI Coding Agents
-
WebBrain: Open-Source Local AI Browser Agent for Task Automation
-
Show HN: Dart_agent_core – Run AI Agents in Flutter Apps with Lifecycle Hooks
-
Ollama Integrated Into Recipe Collection for Intelligent Cooking Assistant
-
Using a local iPhone MCP server to plan Apple Watch workouts with Codex
-
Ask HN: How do you provide your AI agents with access to credentials/secrets?
-
Meet EverOS: An Open Source Markdown-First Agent Memory Runtime With Hybrid BM25 + Vector Retrieval
-
Show HN: Brain.md – A Persistent Memory Layer for Your Coding Agents
-
Using Local Coding Agents
-
Hermes MoA Virtual Models: 8% Higher Than Opus 4.8, 11% Higher Than GPT 5.5
-
Apple's M7 Chip Delivers 56% Memory Bandwidth Increase for On-Device AI
-
Building Tool-Using Agents With Local LLMs
-
Local AI Orchestrator with Computer and Browser Access
-
DeepSWE v1.1 – Updated Execution and Grading for Software Engineering Tasks
-
Build Your Own Local AI Coding Agent with Gemma 4 and OpenCode
-
An Analysis on Why LLMs Perform Badly on Long Loop Tasks
-
Mac Mini Positioned as Premier On-Device AI Computer for Local LLM Inference
-
Founders OS – Self-Hosted AI with Real Business Context
-
Yann LeCun on World Models: Enabling the Next AI Revolution
-
Lessons from Building Evals for Financial AI Agents
-
MCP Server Enables Claude to Automate Mac Tasks and Self-Correct
-
The AI Definition of Done: Establishing Quality Standards Beyond Human Review
-
Agentic Systems Course: Learn to Build AI Agents with Live AI Coding
-
I Gave a Local LLM Access to My Docker Containers, and It Replaced My Monitoring Scripts
-
PageToMD – A CLI tool to turn web pages into clean Markdown for AI agents
-
Show HN: I built an 11-LLM consensus engine to detect AI hallucination
-
Unreal Engine 5.8 Adds MCP Server for AI Agents
-
Self-Organizing Obsidian Vault Powered by Autonomous AI Agents
-
Hermes Agent Framework Extends Local LLMs with Script and Job Execution
-
Local LLM Agents Enable Docker Container Monitoring and Automation
-
Qwen and Fable: Open-Weights 35B Mixture-of-Experts Agentic Coding Model
-
ProData AI – 14 MCP Tools for Automated Data Science
-
Hermes Agent Transforms Local LLMs Into Executable Agents
-
CoreMCP – MCP Server for On-Prem Databases
-
Local-First TypeScript Guard for Runaway AI-Agent Costs
-
CacheWise Optimizes KVCache Reuse for LLM Coding Agents
-
My Local LLM and Claude Are Helping Me Make My Dream Game, One Day at a Time
-
Why Tool Calling is More Important Than Model Size for Local LLMs
-
Repo-Slopscore: Detecting AI Contributions in Git Repositories via Commit Analysis
-
Paca: Lightweight Jira Alternative for Human-AI Collaboration
-
CursorBar: Monitor Local AI Agent Spending and Status in macOS MenuBar
-
Agribrain: Specialized AI Agents for Agricultural Modeling with Local Inference
-
Hybrid Local-Cloud Architecture: Local LLMs with Smart Claude Fallback
-
Show HN: Tail Panic – a multiplayer game designed for AI agents
-
Show HN: SpadeBox – Sandboxed tools and JavaScript runtime for AI agents
-
Outpost – Capability-based API access for AI agents
-
AI can control your desktop through scripts
-
Tool Calling Capabilities Essential for Practical Local LLM Agents
-
Qualcomm Launches Dragonwing MBM Silicon with Advanced On-Device AI Capabilities
-
Prefill Once, Fan Out: KV Snapshot Sharing for Multi-Agent LLM Pipelines
-
Apple Unveils AFM 3 Core Advanced with 20 Billion Parameters for On-Device AI
-
CoAnalyst360: Multi-Agent AI Platform for Investigative Questions
-
Tinytasktree – Behavior-tree-style task orchestration for LLM agents
-
Pizx – zx and Pi AI = shell scripting with 15 AI agent patterns
-
Qualcomm's Dragonwing IQ10 RRD Fast-Tracks Robots From Prototype to Production Deployment
-
Show HN: Akmon, Verify What an AI Agent Did Offline Using Only OpenSSL
-
Maybe Coding Agents Don't Need a Bigger Memory. Maybe They Need Continuity
-
Sawtooth – An Async, Multi-Tiered Memory Framework for LLM Agents
-
Show HN: CLI for Scoring OpenAPI for LLM Legibility
-
N8n-Style Tool Chains for AI Agents – Custom Design and Emergent Behaviors
-
Show HN: LLM Memory Without Context Bleed – 100% Precision vs. <10% Vector Search
-
Bosgame Launches VTA-439 Mini PC with 86 TOPS for Practical Local AI
-
LLM Memory Systems Benchmark: High Recall, Near-Zero Precision for Tested Systems
-
Exploration Got Cheap. Human Review Did Not
-
NanoClaw Founder on OpenClaw's Security Issues: 800k Lines of Code, Sloppiness and Poor Security
-
Google Releases Gemma 4 12B: Encoder-Free Multimodal Model for 16GB Laptops
-
Perplexity Unveils Hybrid Local-Cloud Inference System for Intelligent Task Distribution
-
Snapdragon C Processor Brings On-Device AI Engine to Wearables and Edge Devices
-
MDMA – Turn LLM Responses into Interactive UI via MCP
-
NVIDIA and Microsoft Team Up to Bring Secure On-Device AI Agents to Windows PCs
-
Meet Memory OS: A 6-Layer Open-Source Memory Stack Built on Hermes Agent
-
From Specialists to Builders: How AI Agentic Coding Is Reshaping Software Teams
-
NVIDIA Levels Up Local AI Agents Across RTX PCs and DGX Spark
-
Proveyouragent: Cryptographic Identity for AI Agents (Ed25519 and DPoP)
-
Liquid AI Launches Edge-Focused LFM2.5 Model to Power On-Device AI Agents
-
Microsoft and Nvidia to Unveil First Windows PCs with Nvidia CPUs and AI Capabilities
-
Show HN: Egress WAF to Limit AI Agents and NPM Malware Based on mitmproxy
-
Three Flavors of Coding with AI Agents
-
Rsync 3.4.3 Features Hundreds of Claude Commits
-
Rewriting CRIU in Zig using LLM
-
Liquid AI Unveils Edge-Focused LFM2.5 Model for On-Device AI Agents
-
The Infrastructure Behind Making Local LLM Agents Actually Useful
-
Superpowers: An Agentic Skills Framework for AI Coding Workflows
-
Money Printer Pro – Open-source AI Content Generator
-
MCP Security Flaws Are Turning AI Infrastructure Into a Supply-Chain Risk
-
OpenBMB Runs Local Agents with MiniCPM5-1B – Efficient LLM for Edge Deployment
-
Show HN: I Built a Debugging Challenge for the AI Coding Age
-
AgentSlice – Make AI Coding Agents Ask Before They Edit
-
MCP Servers Transform Local LLM Stack, Replacing $249 Paid Tools
-
Google Adds llms.txt Check to Chrome Lighthouse
-
A Maintainability Ratchet for AI-Assisted Python
-
Deploying Hermes Agent for Free on AMD Developer Cloud with Open Models and vLLM
-
llama.cpp MTP Leak Fix Stabilizes Local AI Agents
-
llama.cpp Checkpoint Fix Accelerates Local Coding Agents
-
Google's Cormac Brick on Tiny LLMs for On-Device Agents
-
Meta Plans Agentic AI on Smartphones and Wearables by 2026
-
OpenAI Agents SDK Ported to React Native for Mobile Deployment
-
Samsung's Exynos 2800 Could Be the First Mobile Chip to Use HBM for Powerful On-Device AI
-
eXo MCP Server Enables Secure AI Agent Access to Workplace Tools
-
Bito's AI Architect Improves Claude Opus Task Success Rate by 35%
-
Local LLMs Enable Intelligent Smart Camera Control Without Cloud Dependency
-
N8n-MCP: AI Assistants Can Now Build and Search n8n Workflows
-
Avocado Studio: Open-Source AI Content Editor for Next.js Sites
-
Researchers Report AI Breaking Every Benchmark for Autonomous Cyber Capability
-
Legacy System Analysis with AI Reveals Modern Architecture Under the Hood
-
What If AI Systems Weren't Chatbots?
-
Microsoft Researchers Find AI Models and Agents Can't Handle Long-Running Tasks
-
DFlash Speculative Decoding Delivers 8.5x Speed Improvement for LLM Inference
-
Deploying Frigate & Ollama On A Minisforum MS-A2 Server
-
0ctx – Local-First Project Memory for AI Workflows
-
Show HN: A Local-First Agentic Knowledge Manager
-
Running Espressif's OpenClaw-Inspired AI Agent on ESP32 with Self-Hosted LLM Works in Practice
-
Show HN: Runs AI Coding Agents Inside Isolated Docker Containers
-
Ask HN: Real life autonomous AI Agents
-
Show HN: Desktop Agent Center – Local AI Automation via Hotkeys
-
Agentic AI Community Focus: Building Local Agents in 2026
-
Show HN: Memex, Claude Memory via Local RAG with MCP and Offline Embeddings
-
Show HN: Claude Relay – Local Claude Code Sessions Message Each Other
-
Building a Jira Alternative with Claude in 8 Days
-
Ruflo: Multi-Agent AI Orchestration for Claude Code
-
Eval Skills for AI Agents
-
Daintree: A Delegation Environment for Orchestrating AI Coding Agents
-
Show HN: Kit – Editor, Browser, Terminal, Mail with AI Agents Sharing Context
-
Show HN: Enoch – Control Plane for Autonomous AI Research
-
Local AI Just Got Easier on Windows and the Implications Go Beyond the Benchmark
-
How to Test AI Agents When They Never Give the Same Answer Twice
-
ScopeGuard 0.0.7: Go Linter with Model Context Protocol Support
-
Show HN: Filling PDF Forms with AI Using Client-Side Tool Calling
-
AI Coding Tools Are Silently Disagreeing with Each Other
-
Xmemory: Benchmarking Structured AI Memory Against RAG and Hybrid RAG
-
96.8% of MCP Tool Descriptions Don't Warn the Agent About Destructive Behaviour
-
Show HN: Arkloop – Open-Source, Local-First Agent Client
-
GraphOS: Visual Runtime and Debugger for AI Agents with Local-First Execution
-
NVIDIA Nemotron 3 Nano Omni Powers Multimodal Agent Reasoning in a Single Efficient Open Model
-
Show HN: Minimal Linux Sandboxes to Manage AI-Generated Code with Ease
-
Thinking Outside the Box: New Attack Surfaces in Sandboxed AI Agents
-
SiGit Code: Local-First Coding Agent
-
Rust Open-Source Headless Browser for AI Agents and Web Scraping
-
Show HN: A Karpathy-Style LLM Wiki Your Agents Maintain
-
Externalization in LLM Agents: Unified Review of Memory and Harness Engineering
-
Cortex Auth – Rust secrets vault for AI agents (exec-based injection)
-
Tesseron: New API Framework for AI Agents with Developer-Defined Configuration
-
Developer Turns Phone Into Local LLM Server with Vision, Voice, and Tool Calling Capabilities
-
ZeusHammer: Built an AI Agent That Thinks Locally
-
Web Agent Bridge: Open-Source OS for AI Agents
-
Build a More Secure, Always-On Local AI Agent with OpenClaw and NVIDIA NemoClaw
-
When Should AI Step Aside?: Teaching Agents When Humans Want to Intervene
-
The Case for Out-of-Process Enforcement for AI Agents
-
Show HN: An MCP server that lets AI compose music on a hardware synth
-
ChatMCP – Connect your AI browser chats to your coding agents
-
GBrain – System to Make Your AI Agent Better Reflect You
-
Local LLM Connected to Home Assistant via MCP Now Enables Autonomous Smart Home Management
-
Defender – Local Prompt Injection Detection for AI Agents
-
Rapidly Scaffold Agents, MCP Servers, APIs, Websites on AWS
-
Universal Knowledge Store and Grounding Layer for AI Reasoning Engines
-
MiniMax M2.7 Is Now Open Source
-
MiniMax M2.7 Advances Scalable Agentic Workflows on NVIDIA Platforms for Complex AI Applications
-
Google's Gemma 4 Brings Free Agentic AI to Your Phone With Zero Data Leaving the Device
-
I Gave My AI Shell Access and Felt Uneasy – So I Sandboxed It
-
Critical Unsloth Gemma-4 Chat Template Updates for Tool Calling
-
Self-Installing Skill Manager for AI Agents
-
GLM 5.1 Dominates Agentic Benchmarks, Outperforming Most Models at 1/3 Opus Cost
-
AI Workflow Evolution: From Prompts to Near-Autonomous Systems
-
Gemma 4 Template Improvements Enhance Tool Use and Dialog Compliance
-
Mano-P: Open-Source On-Device GUI Agent, #1 on OSWorld Benchmark
-
Run Qwen3.5 on an Old Laptop: A Lightweight Local Agentic AI Setup Guide
-
Octopoda: Open Source Memory Layer for Fully Offline AI Agents
-
Gemma 4 26B Achieves Impressive Local Performance With Proper Configuration
-
Real-time Multimodal AI on Apple Silicon: Gemma E2B Demo Shows Practical Edge Deployment
-
Vektor – Local-First Associative Memory for AI Agents
-
Satsgate: Monetize AI Agents and APIs with Lightning L402 Protocol
-
Gemma 4 31B Achieves Third Place on FoodTruck Bench, Beating Larger Models
-
Run AutoGEN with Ollama and LiteLLM in Simple Steps
-
5 Useful Docker Containers for Agentic Developers
-
Nex Life Logger: Local Activity Tracker with AI Agent Integration
-
YC-Bench: GLM-5 Matches Claude Opus 4.6 at 11× Lower Cost
-
SkillCompass – Diagnose and Improve AI Agent Skills Across 6 Dimensions
-
NVIDIA Accelerates Gemma 4 for Local Agentic AI on RTX GPUs
-
Google Launches Gemma 4 Open Models for Local On-Device AI
-
Gemma 4 Makes Local AI Agents Practical
-
Gemma 4 Shows Strong Reasoning Performance with Thinking Tokens
-
Show HN: Memsearch – Persistent, Cross-Agent, Cross-Session Memory for AI Agents
-
Gemini CLI – Open-Source AI Agent for Terminal Integration
-
If Your AI Agent Ran NPM Install During the Axios Attack, You're Compromised
-
Claw64 – Full Agentic Loop in <4KB on Commodore 64
-
Claude Code Source Leaked: Community Extracts Multi-Agent Orchestration Framework
-
Orca – Executable skills and capabilities for AI agent workflows
-
Ollama Launches Pi: The Minimal Coding Agent That Powers OpenClaw Is Now Yours to Customize
-
Scion: Running Concurrent LLM Agents with Isolated Identities and Workspaces
-
Lat.md: Agent Lattice – A Knowledge Graph for Your Codebase in Markdown
-
Local AI Ecosystem Extends Far Beyond Ollama
-
Forensic Beats Mem0 with 90.1% on LOCOMO Benchmark
-
Reverse-Engineering the Apollo 11 Code with AI
-
Why Your AI Agents Will Turn Against You
-
Book on AI Agents for the Layman: Understanding Agent-Based Systems
-
See What Your AI Agents Are Doing: Multi-Agent Observability Tool
-
Meta Releases HyperAgents: Self-Improving AI
-
AI Slop or Quality Storytelling? – Dune Themed MCP Gateway Tutorial
-
OmniCoder v2 Released: Improved Code Generation for Local Deployment
-
Show HN: Open Agent Spec – Treat AI Agents Like Typed Functions, Not Prompt Chains
-
Council: A Structured Deliberation Protocol Across Diverse AI Models
-
AI Agents Can Autonomously Perform Experimental High Energy Physics
-
Self-Hostable AI Agents and Internal Software Framework Released
-
Qwen 3.5 122B Uncensored (Aggressive) Released with New K_P Quantisations
-
Careless Whisper – Personal Local Speech to Text
-
Developer Builds Fully Local Multi-Agent System Using vLLM and Parallel Inference
-
ik_llama.cpp Fork Delivers 26x Faster Prompt Processing on Qwen 3.5 27B
-
A Little Gap That Will Ensure the Future of AI Agents Being Autonomous
-
Running an AI Agent on a 448KB RAM Microcontroller
-
Pydantic-Deep: Production Deep Agents for Pydantic AI
-
Cybersecurity Skills for AI Agents – agentskills.io Standard Implementation
-
Cursor's Composer 2 Model Analysis – Fine-Tuned Variant of Kimi K2.5
-
Claude Code Permissions Hook – Delegate Permission Approval to LLM
-
Hugging Face Releases One-Liner for Automatic Hardware Detection and Model Selection
-
LucidShark – Local-first, open-source quality and security gate
-
Skills Manager – manage AI agent skills across Claude, Cursor, Copilot
-
Show HN: Process Mining for AI Agent Systems
-
OpenJarvis: Local-First AI Agents That Run Entirely On-Device
-
Local Qwen Models Master Browser Automation Through Iterative Replanning
-
How I Used Lima for an AI Coding Agent Sandbox
-
Mistral Releases Leanstral: First Open-Source Code Agent for Lean 4 Proof Assistant
-
The Moment AI Agents Stopped Being a Feature and Started Becoming a System
-
How AI Agents Should Pay for API Calls: X402 and USDC Verification on Base
-
Dictare – Open-source Voice Layer for AI Coding Agents (100% Local)
-
AMD Declares 'AI on the PC Has Crossed an Important Line' – Agent Computers as Next Breakthrough
-
Show HN: Buxo.ai – Calendly alternative where LLM decides which slots to show
-
Hybrid AI Desktop Layer Combining DOM-Automation and API-Integrations
-
Show HN: Bots of WallStreet – Multi-Agent Debate and Prediction Framework
-
Memory Should Decay: Implementing Temporal Memory Decay in Local LLM Systems
-
Show HN: Intake API – An Inbox for AI Coding Agents
-
AgentArmor: Open-Source 8-Layer Security Framework for AI Agents
-
3-Path Agent Memory: 8 KB Recurrent State vs. 156 MB KV Cache at 10K Tokens
-
MeepaChat – Slack for AI Agents (iOS, macOS, Web / Cloud, Self-Hosted)
-
Nvidia Releases Nemotron 3 Super: 120B MoE Model for Local Deployment
-
Ex-Manus Backend Lead Shares: Moving Beyond Function Calling in Agent Design
-
A Kubernetes Operator That Orchestrates AI Coding Agents
-
Researchers Gave AI Agents Real Tools. One Deleted Its Own Mail Server
-
Mnemos: Persistent Memory System for Local AI Agents
-
.ispec: Runtime Specification Validation for AI System Consistency
-
Bash-Based Claude Code Agent: Lightweight Local AI Coding Assistant
-
Qwen 3.5 Ultra-Compact Models Enable On-Device AI from Watches to Gaming
-
VS Code Agent Kanban – Task Management for AI-Assisted Development
-
Qwen 3.5 Family Benchmark Comparison Shows Strong Performance Across Smaller Models
-
Nemotron 9B Powers Large-Scale Local Inference: Patent Classification and Real-Time Applications
-
Gyro-Claw – Secure Execution Runtime for AI Agents
-
Engram – Open-Source Persistent Memory for AI Agents
-
AI Agent Reliability Tracker
-
Show HN: Ivy – the first proactive, offline AI tutor
-
Mistral AI Prepares Workflows Integration for Le Chat
-
OpenSpec: Spec-driven development (SDD) for AI coding assistants
-
Benchmark: Local Open-Source LLMs Competitive in Real-Time Trading Applications
-
ETH Zurich Research Challenges Context-Length Assumptions in LLM Agents
-
Show HN: SimplAI – Build and Deploy AI Agents and Workflows Without Boilerplate
-
Open WebUI Adds Native Terminal Tool Calling with Qwen3.5 35B Support
-
Show HN: BoardMint – A PCB Review Tool That Avoids AI Hallucinations
-
Real-World Qwen 3.5 9B Agent Performance on M1 Pro Validates Edge Deployment
-
llama.cpp Merges Agentic Loop and MCP Client Support
-
Imrobot – Reverse-CAPTCHA for Verifying AI Agents, Not Humans
-
ConsciOS v1.0: A Viable Systems Architecture for Human and AI Alignment
-
Analysis Reveals Claude Code Sends 62,600 Characters of Tool Definitions Per Turn
-
Kakao Launches Kanana AI for On-Device Schedule and Recommendation Management
-
Incrmd: Incremental AI Coding by Editing PROJECT.md
-
SynthesisOS – A Local-First, Agentic Desktop Layer Built in Rust
-
ÆTHERYA Core – Deterministic Policy Engine for Governing LLM Actions
-
Framework Choice Critical: llama.cpp and vLLM Outperform Ollama for Qwen 3.5 Testing
-
RAG vs. Skill vs. MCP vs. RLM: Comparing LLM Enhancement Patterns
-
Browser Use vs. Claude Computer Use: Comparing Agent Automation Frameworks
-
Alibaba's Open-Source CoPaw AI Agent Now Compatible with MCP and ClawHub Skills
-
Configure MCP Servers Once, Sync Them Everywhere
-
AgentLens – Open-Source Observability for AI Agents
-
5 Useful Docker Containers for Agentic Developers
-
Qwen3.5-35B Unsloth Dynamic GGUFs Achieve SOTA Across Nearly All Quantisation Levels
-
We Audited the Security of 7 Open-Source AI Agents – Here Is What We Found
-
Show HN: MCP Server for AI Compliance Documentation
-
Enclave Gem: Mega Useful if You're Building Agents on Ruby on Rails
-
On-Device Function Calling in Google AI Edge Gallery
-
Arduino, Qualcomm Bring On-Device AI and Robotics Learning to Indian School Systems
-
5 Useful Docker Containers for Agentic Developers
-
Show HN: AgentGate – Stake-Gated Action Microservice for AI Agents
-
Every agent framework has the same bug – prompt decay. Here's a fix
-
DeepSeek Releases DualPath: Addressing Storage Bandwidth Bottlenecks in Agentic Inference
-
Agent System – 7 specialized AI agents that plan, build, verify, and ship code
-
Show HN: A Human-Curated, CLI-Driven Context Layer for AI Agents
-
Qwen3.5-35B-A3B Emerges as Game-Changer for Agentic Coding Tasks
-
PyTorch Foundation Announces New Members as Agentic AI Demand Grows
-
Show HN: MCP-Enabled File Storage for AI Agents, Auth via Ethereum Wallet
-
What Breaks When AI Agent Frameworks Are Forced Into <1MB RAM and Sub-ms Startup
-
Show HN: Dypai – Build Backends from Your IDE Using AI and MCP
-
Comparing Manual vs. AI Requirements Gathering: 2 Sentences vs. 127-Point Spec
-
Enterprise Infrastructure Guide: Running Local LLMs for 70-150 Developers
-
Show HN: Agora – AI API Pricing Oracle with X402 Micropayments
-
Which Web Frameworks Are Most Token-Efficient for AI Agents?
-
Show HN: The Only CLI Your AI Agent Will Need
-
GPT-OSS 20B Demonstrates Practical Agentic Capabilities Running Fully Locally
-
Breaking the Speed Limit: Strategies for 17k Tokens/Sec Local Inference
-
Massu: Governance Layer for AI Coding Assistants with 51 MCP Tools
-
The Complete Stack for Local Autonomous Agents: From GGML to Orchestration
-
Claude Code Open – AI Coding Platform with Web IDE and Agents
-
Apple Researchers Develop On-Device AI Agent That Interacts With Apps for You
-
24 Simultaneous Claude Code Agents on Local Hardware
-
SanityBoard Adds 27 New Model Evaluations Including Qwen 3.5 Plus, GLM 5, and Gemini 3.1 Pro
-
TemplateFlow – Build AI Workflows, Not Prompts
-
Why AI Models Fail at Iterative Reasoning and What Could Fix It
-
Show HN: Forked – A Local Time-Travel Debugger for OpenClaw Agents
-
Cloudflare Releases Agents SDK v0.5.0 with Rust-Powered Infire Engine for Edge Inference
-
Ask HN: How Do You Debug Multi-Step AI Workflows When the Output Is Wrong?
-
I attacked my own LangGraph agent system. All 6 attacks worked
-
Show HN: Inkog – Pre-flight check for AI agents (governance, loops, injection)
-
I broke into my own AI system in 10 minutes. I built it
-
Security Alert: Open Claw Designed for Self-Hosting, Stop Sharing Credentials
-
InitRunner: YAML-Based AI Agent Framework with RAG and Memory
-
MiniMax Releases M2.5 Model with SOTA Coding and Agent Capabilities
-
Qwen Coder Next Shows Specialized Agent Performance
-
GLM-5 Released: 744B Parameter MoE Model Targeting Complex Tasks
-
Use Recursive Language Models to address huge contexts for local LLM
-
5 Practical Ways to Use Local LLMs with MCP Tools
-
Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts