3/26/2026
FreeLipSync: AI Video Translator and Automatic Lip-Sync Dubbing Tool
FreeLipSync: AI video translation and lip-sync dubbing tool supporting 100+ languages with 98% accuracy and no registration required.
3/26/2026
GitHub hits CTRL-Z, decides it will train its AI with user data after all
GitHub will train AI models on customer data from Copilot Free/Pro starting April 24; enterprise users exempt; opt-out available.
3/26/2026
Show HN: Cc-Lens, Open Source Analytics Dashboard for Claude Code
Local analytics dashboard for Claude Code monitoring with real-time refresh, reading from local ~/.claude/ directory without cloud telemetry.
3/26/2026
Run and manage open-source LLMs from your terminal
LLM-Launchpad: CLI tool for running open-source LLMs on Modal with terminal UI for managing endpoints and model deployments.
3/26/2026
Top AI models underperform in languages other than English
Research finding that leading LLMs significantly underperform in non-English languages, with accuracy gaps widening across domains.
3/26/2026
Why Responsible AI Is the Bedrock of AI-Powered Applications
Discussion of responsible AI principles for agent and chatbot deployment, emphasizing safety and user experience.
3/26/2026
Rses – cross-resume between Claude Code, Codex, and OpenCode
CLI tool enabling session resumption across Claude Code, Codex, and OpenCode with structured handoff protocol. ~1200 lines, minimal dependencies.
3/26/2026
Large-scale online deanonymization with LLMs
Research on large-scale deanonymization attacks using LLMs. Privacy and security implications for online systems.
3/26/2026
Show HN: Alexandria, free open source news aggregation and classification suite
News aggregation suite using NLP classification with Docker microservices, RabbitMQ, and custom labeling. CPU-based processing without GPU optimization.
3/26/2026
Show HN: Agentic Commerce Marketplace
Open-source e-commerce marketplace with agentic commerce capabilities and flexible adapter system, alternative to Shopify.
3/26/2026
Show HN: Agent Flow: A beautiful way to visualize Claude Code actions
Tool for visualizing Claude Code agent execution in real-time, showing problem decomposition, tool selection, and agent coordination with debugging capabilities.
3/26/2026
Meta releases HyperAgents: self-improving AI
Meta releases HyperAgents: self-improving AI agents using self-referential optimization for arbitrary computable tasks with code execution.
3/26/2026
MCP-Manticore: Let Your AI Assistant Write Manticore Queries for You
MCP integration enabling AI assistants to write Manticore search queries automatically.
3/26/2026
Show HN: //Beforeyouship is a pre-build tool to estimate the LLM cost
Pre-build cost estimation tool for LLM selection, addressing tokenization and pricing math for solo developers building AI applications.
3/26/2026
Show HN: Imrobot – Reverse CAPTCHA that verifies AI agents, not humans
Reverse CAPTCHA for verifying AI agents instead of humans. npm package and live demo. For agent-facing APIs and multi-agent authentication.
3/26/2026
Running Sonnet 4.5 Level LLM's on Your Own Servers: Kimi K2.5 Economics
Economics analysis of running Kimi K2.5 (Sonnet 4.5-level) LLM on own servers vs. cloud inference.
3/26/2026
Paper: Reducing hallucination in English–Hindi LLMs using citation grounding
Research on reducing hallucination in English-Hindi LLMs through citation grounding technique.
3/26/2026
SidClaw – The approval layer for AI agents (open-source)
SidClaw: Open-source governance layer for AI agents adding policy evaluation, human approval, and audit trails without code changes.
3/26/2026
Show HN: An x402 gateway for buying a finished local business website
HTTP 402 gateway for local business website builder with LLM research, image analysis, and agentic deliverables pipeline.
3/26/2026
Show HN: Neural DNA – 258 params that grow network topology
Neural network topology grown from 258-parameter genome using developmental rules. Achieves 8,384:1 compression, sparse connectivity matches dense baselines, transfers across tasks. Python implementation for M3/CPU.
3/26/2026
RuntimeGuard v2 – enforcement and easy security posture config for AI agents
RuntimeGuard v2: Open-source MCP server enforcing security policies on AI agent file/shell actions before execution. Local-first, no account required.
3/26/2026
Chonkify – compression for RAG and Agents that outperforms LLMLingua by ~4 times
Chonkify compression tool for RAG and agents, claims 4x improvement over LLMLingua.
3/26/2026
Modly: Drop a photo, get a 3D mesh, open source and runs on your GPU
Open source desktop app converting photos to 3D meshes using GPU-local inference. Runs on user's hardware without cloud upload.
3/26/2026
Agent Identity System
Protocol for agent authentication, authorization, accountability, and payment to solve API setup barriers for long-horizon autonomous agents.
3/26/2026
70% of new software engineering papers on ArXiv are LLM related
Analysis of ArXiv software engineering papers: 70% LLM-related since 2022, showing dominance of LLM research focus.
3/26/2026
Show HN: Book Grounded AI Learning
Tool using LLMs grounded in books for learning: provides book summaries and expert validation by linking AI to authoritative sources.
3/26/2026
HDP: An open protocol for verifiable human authorization in agentic AI systems
HDP protocol provides cryptographic chain-of-custody for agentic AI systems, ensuring human authorization is traceable through agent delegation chains.
3/26/2026
Rule based automation vs. Agentic AI system
Comparison of rule-based automation (Tasker, MacroDroid) versus agentic AI systems for mobile automation on Android platforms.
3/26/2026
LiteLLM Supply Chain Attack: Defense in Depth Is the Only AI Security Strategy
LiteLLM open-source LLM proxy suffered a supply chain attack in March 2026 where backdoored packages harvested credentials for three hours, demonstrating need for defense-in-depth security strategies.
3/26/2026
Show HN: Orloj – agent infrastructure as code (YAML and GitOps)
Open-source orchestration runtime for multi-agent AI systems using declarative YAML manifests. GitOps approach to agent governance and workflows.
3/26/2026
Show HN: Agent Ruler new update v0.1.9
Agent Ruler v0.1.9 update: reference monitor with confinement for AI agent workflows, adding security/safety layer outside agent guardrails.
3/26/2026
Prompt Guard – MitM proxy that blocks credentials before they reach AI APIs
HTTPS MITM proxy intercepting prompts to AI APIs/assistants, detecting and blocking sensitive data before transmission to third-party servers.
3/26/2026
Show HN: Agent Kernel – Three Markdown files that make any AI agent stateful
Three markdown files enabling stateless AI agents to maintain memory across sessions using git repos. Works with coding agents like Claude, Cursor, Windsurf.
3/26/2026
HN: Surviving the litellm supply chain attack with a pure ctypes OS Vault
Local-first AI orchestration framework (MACCREv2) designed to avoid trusting third-party wrappers with API keys/filesystem. Response to litellm supply chain attack.
3/26/2026
Research Shows Verbatim Recall of Copyrighted Books in LLMs
Research study demonstrating verbatim recall of copyrighted books in finetuned LLMs across cross-author and within-author scenarios
3/26/2026
PLDR-LLMs Reason At Self-Organized Criticality
Theoretical analysis of LLM reasoning properties at self-organized criticality with connections to phase transitions and scaling functions.
3/26/2026
Environment Maps: Structured Environmental Representations for Long-Horizon Agents
Environment Maps: Persistent agent-agnostic representation for reducing cascading errors in long-horizon LLM-based software automation tasks.
3/26/2026
Evaluating a Multi-Agent Voice-Enabled Smart Speaker for Care Homes: A Safety-Focused Framework
Safety-focused evaluation framework for multi-agent voice-enabled smart speaker in care homes covering resident data access and task scheduling.
3/26/2026
Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments
EnterpriseArena: Benchmark evaluating LLM agents as CFOs for resource allocation under uncertainty in dynamic business environments.
3/26/2026
GTO Wizard Benchmark
Public API and evaluation framework for benchmarking poker algorithms against GTO Wizard, a superhuman HUNL poker agent.
3/26/2026
Grounding Vision and Language to 3D Masks for Long-Horizon Box Rearrangement
Method for long-horizon 3D box rearrangement using vision-language grounding and 3D masks for multi-step planning from natural language.
3/26/2026
LLMs Do Not Grade Essays Like Humans
Evaluation comparing LLM essay scoring with human grading across GPT and Llama models, finding weak agreement in standard settings.
3/26/2026
Efficient Benchmarking of AI Agents
Study on efficient benchmarking of AI agents showing how task subsets can preserve agent rankings while reducing evaluation costs.
3/26/2026
Learning-guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation
Learning-guided prioritized planning combining ML and search-based solvers for lifelong multi-agent pathfinding in warehouse automation.
3/26/2026
VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents
VehicleMemBench: Benchmark for evaluating long-term memory in multi-user in-vehicle agents handling preference conflicts and temporal dynamics.
3/26/2026
SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systems
SCoOP: Training-free uncertainty quantification framework for multi-VLM systems using semantic-consistent opinion pooling.
3/26/2026
The DeepXube Software Package for Solving Pathfinding Problems with Learned Heuristic Functions and Search
DeepXube: Free open-source Python package for pathfinding using learned heuristic functions from deep RL and search algorithms.
3/26/2026
DUPLEX: Agentic Dual-System Planning via LLM-Driven Information Extraction
DUPLEX: Neuro-symbolic agentic architecture combining LLMs with schema-guided information extraction for robust robotic task planning in long-horizon domains.
3/26/2026
AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents
AnalogAgent: LLM-based agentic framework for automated analog circuit design using multi-model loops to preserve domain-specific insights and context.
3/26/2026
From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments
Empirical study analyzing 2000+ RL papers to create quantitative taxonomy of reinforcement learning environments and technological trends.