2/23/2026
Show HN: EloPhanto – A self-evolving AI agent that builds its own tools
EloPhanto self-evolving local AI agent that controls Chrome browser with 47 tools. Autonomously writes, tests, and integrates new Python tools.
2/23/2026
Show HN: A2SPA – Cryptographic payload signing and verification for AI agents
A2SPA cryptographic tool for signing and verifying AI agent payloads. Security infrastructure for agent communication.
2/23/2026
TinySDLC – Agent orchestrator with SDLC role discipline for AI coding (MIT)
TinySDLC agent orchestrator adds SDLC discipline to multi-agent AI coding. Eight roles with separation of duties, isolated workspaces, enforced handoffs.
2/23/2026
Show HN: Vram.run – Compare API providers, local GPUs, and cloud for any model
Vram.run is a comparison tool for API providers, local GPUs, and cloud options across different LLM models.
2/23/2026
Show HN: Kwin-MCP – MCP server for AI-driven Linux GUI automation via KWin
Kwin-MCP server enables AI agents to automate Linux GUI via KWin. MCP protocol for AI-driven desktop automation.
2/23/2026
Show HN: Vibevideo – Unified interface for top AI video models
Vibevideo unified interface for multiple AI video generation models. Aggregates text-to-video, frame-guided, and reference-based generation tools.
2/23/2026
Show HN: Mindpm – persistent project/task memory for AI coding assistants (MCP)
mindpm MCP server adds persistent memory to AI coding assistants across Claude Code, Cursor, and others. Stores tasks and decisions in SQLite.
2/23/2026
How we built a chat-with-data agent that doesn't AI generate SQL
Inconvo agent builder enables chat-with-data without LLM SQL generation. Validates structured intents against semantic layer before execution.
2/23/2026
Show HN: Fiscal – An Agent Friendly CLI for Actual Budget
Open-source CLI tool for Actual Budget optimized for AI agents like Claude Code, enabling programmatic budget management while maintaining web dashboard access.
2/23/2026
How to automate AI agents to read Jira tickets and create pull requests
Tutorial on using AI agents to automate reading Jira tickets and generating pull requests.
2/23/2026
Deep-Dive into LLM Fine-Tuning
Guide to fine-tuning LLMs for enterprise applications, covering mechanics of adapting models like Qwen 3 and DeepSeek v3 for domain-specific use cases.
2/23/2026
From magic to literacy: ask LLMs for tools, not answers
Conceptual article on requesting tool recommendations from LLMs instead of direct answers.
2/23/2026
Show HN: Track your Codex CLI(5.3) token spending (also Claude Code and Gemini)
toktrack CLI tool monitors token spending across Claude, Codex, and Gemini. Rust-based cost tracking with usage analytics.
2/23/2026
Show HN: MEVA – A lightweight desktop Markdown viewer built with Rust (<15MB)
Lightweight 15MB Markdown file viewer built in Rust, designed for reading AI-generated documentation.
2/23/2026
Show HN: Tickr – AI project manager that lives inside Slack (replaces Jira)
Tickr Slack bot for AI-driven project management. Automates task tracking and team nudges as alternative to Jira.
2/23/2026
Show HN: AI CLI – Translate natural language into shell commands using LLMs
CLI tool that translates natural language commands into shell commands using LLMs, enabling hands-free terminal interaction.
2/23/2026
Show HN: Turl – Curl, but for Agent
CLI tool designed as curl alternative for AI agents to make HTTP requests.
2/23/2026
Show HN: BasaltSurge – Web3 POS checkout and AI-agent commerce API
BasaltSurge payment API designed for AI agents to perform commerce transactions, bypassing legacy card rails with standardized checkout layer.
2/23/2026
A First Look at the Future of the Bloomberg Terminal in the Age of Agentic AI
Bloomberg Terminal redesign integrating agentic AI capabilities for financial analysis and decision-making workflows.
2/23/2026
Show HN: A standardized safety module for robot brains (15 patents, solo)
Hardware and software safety standard for AI-controlled robots with dedicated safety processor on independent power rail controlling AI processor power access.
2/23/2026
NIST Launches Standards Initiative for AI Agents
NIST launches standards initiative for AI agents to establish consistency and safety protocols in agent development.
2/23/2026
Show HN: Attest – Test AI agents with 8-layer graduated assertions
Testing framework for AI agents with 8-layer graduated assertions covering tool calls, cost budgets, schemas, and output validation without relying on LLM judges.
2/23/2026
Show HN: AgentWard – After an AI agent deleted files, I built a runtime enforcer
Runtime permission enforcer for AI agents that prevents file deletion and tool misuse through code-level policies outside LLM context.
2/23/2026
Show HN: Rmux – Terminal multiplexer for LLM, built with Rust and egui
Terminal multiplexer built with Rust and egui designed for LLM interaction and management.
2/23/2026
Show HN: Tron-style multiplayer light-cycle game for LLMs via MCP
Multiplayer game where LLMs control light-cycles via MCP protocol on a grid, testing agent reasoning and decision-making capabilities.
2/23/2026
Show HN: AgentReady – Drop-in proxy that cuts LLM token costs 40-60%
OpenAI-compatible proxy that reduces LLM token costs 40-60% through deterministic rule-based prompt compression with ~5ms overhead.
2/23/2026
Mental Health Escalation Router
Production crisis detection system using AI to identify high-risk distress signals with cryptographic audit trails and formal safety guarantees.
2/23/2026
Managed OpenClaw hosting, 60-second provisioning
Managed hosting service for OpenClaw open-source AI agent framework with 60-second deployment.
2/23/2026
Show HN: SkillScan – Free API to detect malicious AI agent skill files
SkillScan is a free API detecting malicious patterns in AI agent skill files. Identifies exfiltration services, env reads, API key theft, and prompt injection attempts.
2/23/2026
Show HN: Agentic programming needs new processes
Analysis of how AI coding agents require new development processes and workflows beyond traditional productivity measurement.
2/23/2026
Show HN: AI Timeline – 171 LLMs from Transformer (2017) to GPT-5.3 (2026)
Interactive timeline tracking 171 LLMs from Transformer (2017) to GPT-5.3 (2026). Filterable by open/closed source across 54 organizations.
2/23/2026
OpenAI announces Frontier Alliance Partners
OpenAI's Frontier platform for building, deploying, and managing AI coworkers that automate enterprise workflows end-to-end.
2/23/2026
MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation
MALLVI: Multi-agent framework combining LLMs and vision for closed-loop robotic manipulation with environmental feedback, enabling dynamic task planning.
2/23/2026
Wink: Recovering from Misbehaviors in Coding Agents
Wink: Framework for detecting and recovering from misbehaviors in LLM-powered coding agents, addressing issues like instruction deviation, infinite loops, and tool misuse.
2/23/2026
Reducing Text Bias in Synthetically Generated MCQAs for VLMs in Autonomous Driving
Study reducing textual bias in synthetic MCQA benchmarks for vision-language models to prevent exploitation of linguistic patterns in autonomous driving.
2/23/2026
BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMs
BioBridge: Domain-adaptive framework bridging protein language models with LLMs for enhanced biological reasoning and protein interpretation.
2/23/2026
LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
LATMiX: Learnable affine transformations for microscaling quantization of LLMs, improving robustness by reducing activation outliers.
2/23/2026
CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models
CodeScaler: Execution-free reward model scaling code LLM training and inference via verifiable rewards without test case dependencies.
2/23/2026
Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO
Curriculum learning framework for distilling chain-of-thought reasoning into compact student models via structure-aware masking and GRPO training.
2/23/2026
AnCoder: Anchored Code Generation via Discrete Diffusion Models
AnCoder: Code generation via discrete diffusion models using AnchorTree framework to maintain programming language structure and executability.
2/23/2026
Robust Pre-Training of Medical Vision-and-Language Models with Domain-Invariant Multi-Modal Masked Reconstruction
Robust-MMR: Multi-modal pre-training approach for medical vision-language models with domain-invariant masked reconstruction for robustness.
2/23/2026
Tethered Reasoning: Decoupling Entropy from Hallucination in Quantized LLMs via Manifold Steering
HELIX: Geometric framework decoupling entropy from hallucination in quantized LLMs by steering hidden states to truthfulness manifold.
2/23/2026
Agentic Unlearning: When LLM Agent Meets Machine Unlearning
Agentic unlearning framework removing sensitive information from both LLM parameters and agent memory to prevent information reactivation.
2/23/2026
A Case Study of Selected PTQ Baselines for Reasoning LLMs on Ascend NPU
Case study comparing PTQ methods (AWQ, GPTQ, SmoothQuant, FlatQuant) for reasoning LLMs on Ascend NPU hardware.
2/23/2026
AsynDBT: Asynchronous Distributed Bilevel Tuning for efficient In-Context Learning with Large Language Models
AsynDBT: Asynchronous distributed optimization for in-context learning with cloud-based LLM APIs to improve prompt engineering efficiency.
2/23/2026
EXACT: Explicit Attribute-Guided Decoding-Time Personalization
EXACT: Decoding-time personalization for LLMs using explicit attribute-guided adaption to account for context-dependent user preferences.
2/23/2026
Can LLM Safety Be Ensured by Constraining Parameter Regions?
Systematic evaluation of safety region identification methods across LLM families, testing parameter constraints for controlling model safety behaviors.
2/23/2026
Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters
Framework leveraging variability modeling to optimize LLM inference hyperparameters for energy efficiency and computational sustainability.
2/23/2026
ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs
ScaleBITS: Mixed-precision quantization method for LLMs using principled bitwidth search to reduce memory and inference cost below 4-bit average.
2/23/2026
Certified Learning under Distribution Shift: Sound Verification and Identifiable Structure
Framework for certifying ML model risk bounds under distribution shift with verifiable constraints and computable metrics.