3/31/2026
Feat: Open-Source Claude Code
Open-source version of Claude Code announced.
3/31/2026
Show HN: A tool to solve the Agent Supply Chain pandora box
Open-source CLI tool for managing AI agent dependencies, plugins, and skills with manifest and lockfile approach.
3/31/2026
Show HN: Virtui – TUI session automation and recording for agents
Virtui: daemon and CLI enabling AI agents to programmatically control terminal applications via gRPC API for TUI automation.
3/31/2026
In-process circuit breaker that kills runaway AI agents before they go rogue
Circuit breaker library for stopping harmful AI agent actions in real-time with two-line SDK integration and HTTP-level coverage.
3/31/2026
Meta-Harness: End-to-End Optimization of Model Harnesses
Meta-Harness optimizes AI agent evaluation harnesses end-to-end, improving agent performance from 28.5% to 46.5% on 19-task subset.
3/31/2026
Show HN: King Louie a local multi-machine AI assistant
King Louie: open-source Electron-based chat application supporting multiple LLM providers and integration with Telegram, Discord, Slack.
3/31/2026
1-Bit Bonsai: The First Commercially Viable 1-Bit LLMs
1-bit Bonsai announces commercially viable 1-bit quantized LLMs optimized for real-world deployment on resource-constrained devices.
3/31/2026
Node Banana – Open, Local Alternative to Weavy/Flora
Node Banana: open-source node-based workflow editor for AI media generation with multi-provider support and local execution.
3/31/2026
Xenv.sh – the first secrets manager built for AI agents
Xenv.sh: secrets manager built for AI agents with AES-256 encryption, MCP server, and integration with Claude Code and other tools.
3/31/2026
Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs
1-bit Bonsai 8B and 4B: quantized LLMs with 1-bit weights, 14× smaller footprint, 8× faster, designed for edge computing and robotics.
3/31/2026
APS: Open specification for AI agent policies
APS: open specification for AI agent policies enabling declarative controls to block, redact, or transform content and tool invocations.
3/31/2026
Show HN: Fixing Claude Code's amnesia with persistent memory
cmr-memory adds persistent cross-session memory to Claude Code agents using context-activated retrieval instead of fixed MEMORY.md.
3/31/2026
Open Swarm, open source platform for running AI agents in parallel
Open Swarm: locally-running orchestrator for launching and monitoring multiple AI agents in parallel with visual dashboard and coordination.
3/31/2026
ClaudeDown: Is Claude getting dumber, or is it just you?
Analysis of Claude AI performance degradation via complaint tracking metrics. LLM application but lacks technical depth.
3/31/2026
Mercury Edit 2: Fastest next-edit prediction with a diffusion LLM (221ms)
Mercury Edit 2: diffusion LLM achieving 221ms latency for next-edit prediction in code. LLM research for developer tools.
3/31/2026
Ask HN: What custom instructions do you use to minimize LLM sycophancy?
Community discussion on custom instructions to reduce LLM sycophancy. Practical LLM optimization tips.
3/31/2026
The architectural trade-offs of AI code generation
Analyzes architectural trade-offs in AI-powered code generation systems.
3/31/2026
Show HN: The 42-Day Vibe – A mockumentary on "Vibe Coding" taken to the extreme
Mockumentary podcast about LLM agent managing codebase autonomously for 42 days. Explores AI agents in software development.
3/31/2026
A Taxonomy of AI Agents
Proposes taxonomy categorizing AI agents into distinct species based on infrastructure, trust models, and human involvement, addressing ambiguity in how the term 'agent' is used.
3/31/2026
Nexus – Agent-native ops platform for ecommerce MCP, self-registration, no demos
Nexus: agent-native ecommerce ops platform using MCP protocol for AI agent self-registration and integration. AI agents developer tool.
3/31/2026
Agentic AI Engineering Workflows for iOS in 2026
Analysis of AI-driven iOS development workflows and industry shift toward AI-written code in 2026. LLM applications in development.
3/31/2026
Sauver: An open-source, local AI agent that fights email slop
Sauver: open-source local AI agent filtering email spam. MIT licensed, privacy-focused LLM application.
3/31/2026
Show HN: The 42-Day Vibe – A mockumentary on "Vibe Coding" taken to the extreme
Mockumentary podcast about LLM agent managing codebase autonomously for 42 days. Explores AI agents in software development.
3/31/2026
Show HN: Multi-agent autoresearch for ANE inference beats Apple's CoreML by 6×
Multi-agent system optimizing Apple Neural Engine inference 6× faster than CoreML through collaborative learning. AI agents research.
3/31/2026
Show HN: I adapted codex-plugin-cc's design for Gemini CLI's ACP
Open-source TypeScript SDK for CAPTCHA that targets LLM reasoning capabilities rather than human biology.
3/31/2026
Major Claude Code source leak offers deep insight into how Anthropic tool works
Semantic search tool for 29,657 HuggingFace models with natural language queries, optimized for finding small specialized models without embeddings.
3/31/2026
Jailbroken, open-source, pre-built iOS 26 virtual machine
Agent harness tool benchmarked 40% faster and 25-55% cheaper than Claude Code, now available as Claude Code plugin for mobile app building.
3/31/2026
Ask HN: I burnt out from software development. What now?
Platform enabling autonomous AI agents to transact using open protocols with cryptographic verification and reputation scoring.
3/31/2026
Do LLMs Break the Sapir-Whorf Hypothesis?
Research examining whether transformer-based LLMs break the Sapir-Whorf hypothesis about language shaping thought through analysis of reasoning layers.
3/31/2026
GitHub Will Train Copilot Models with User Data by Default
GitHub policy change defaulting to use Copilot interaction data for model training with opt-out available starting April 2026.
3/31/2026
Sprintra – Persistent memory for AI coding agents (MCP-native)
Sprintra adds persistent memory capability to AI coding agents using MCP protocol.
3/31/2026
Claude Code fork that works with any OpenAI-compatible LLM
Open source fork of Claude Code supporting multiple LLM backends (OpenAI, Ollama, vLLM, Groq) with agent toolchain for file editing and task automation.
3/31/2026
Show HN: AI Engineering AI-native Self-learning course repo
Self-learning course repository for AI engineering, appears to be educational content/curriculum.
3/31/2026
CoPaw – A truly local OpenClaw alternative with customized models (2B, 4B, 9B)
CoPaw local AI assistant supporting 2B-9B models with self-hosting, memory control, and skill extensions without vendor lock-in.
3/31/2026
Pipevals: Evaluation pipelines for every LLM application
Pipevals: open-source evaluation pipeline builder for LLM applications. HTTP API integration for quality tracking without SDK wrapper.
3/31/2026
Ask HN: Has anyone benchmarked skill availability impact on LLM performance?
HN discussion asking if anyone systematically benchmarks LLM skills/tools to measure their impact on model performance.
3/31/2026
Get video proof of what your agents did in TUIs
Tool recording AI agent interactions with TUIs as video proof, showing keystrokes and system state with full ANSI color support.
3/31/2026
Show HN: Dograh – voice agents that pick Recordings over TTS using LLM
Dograh open source voice agent platform with drag-and-drop workflows, Gemini 3.1 support, and pre-recorded audio for local deployment.
3/31/2026
Show HN: Domscribe – Deterministic DOM-to-source mapping for AI coding agents
Domscribe tool providing deterministic DOM-to-source mapping for AI coding agents to reduce token usage in frontend automation tasks.
3/31/2026
Open-source security tests for AI agents (MCP, A2A, x402, AIUC-1)
Open source security testing framework for multi-agent AI deployments covering agent escalation, context poisoning, and prompt injection attacks.
3/31/2026
Show HN: An agent skill that tracks SF city hearings, permits, lobbying etc.
OpenClaw skill aggregating 22 SF government data sources to track city hearings, permits, and lobbying decisions.
3/31/2026
Show HN: SuprLogs – Autopilot changelogs from GitHub commits
Tool generating automated changelogs from GitHub commits using LLM analysis of diffs for non-technical audiences.
3/31/2026
A bug in Bun may have been the root cause of the Claude Code source code leak
Report of Bun bundler bug that exposed source maps in production, potentially related to Claude Code source leak.
3/31/2026
Show HN: OpenClaw Arena – Benchmark models on real tasks, rank by perf and cost
OpenClaw Arena benchmark platform comparing AI models on real agentic tasks with tool access, separate leaderboards for performance and cost.
3/31/2026
How we made Trail of Bits AI-native (so far)
Case study on Trail of Bits' AI adoption strategy, building integrated system for 94% employee adoption with 94 plugins.
3/31/2026
Show HN: Open-FDD – On Prem HVAC Fault Detection with OpenClaw, BACnet, & Brick
Open-source on-premises knowledge graph platform for HVAC fault detection using BACnet and Brick, enabling facility energy optimization.
3/31/2026
How HN: Synthetic You – AI calibrated to your personality
Service offering personality-calibrated AI mentor prompts based on psychometric assessments for ChatGPT and Claude.
3/31/2026
AI agent is authorized to do everything wrong
Technical article on authorization failures for autonomous AI agents in production systems, using invoice processing pipeline example.
3/31/2026
Show HN: Fakekey – never expose real API keys in the agent environment
Fakekey open source project preventing API key exposure in AI agent environments through token masking and secure credential handling.
3/31/2026
Show HN: Dewey – Ingest docs, search semantically, get cited AI answers
Dewey tool for ingesting documents and semantic search with hierarchical chunking for RAG and multi-hop reasoning across documents.