Guardians – Verify tool-using agent workflows before execution

What it does

An implementation of the ideas in Erik Meijer's "Guardians of the Agents" (CACM, January 2026). The paper's thesis: the root cause of prompt injection in agentic systems is the same as SQL injection — code and data aren't separated. The fix is the same too. Instead of letting the LLM call tools one at a time and decide what to do after each result, the LLM generates a structured plan upfront using symbolic references (placeholders, not real data). A static verifier checks the plan against a security policy before any tool runs. Only verified plans execute. The verifier uses three independent checks: taint analysis (does data flow from a source to a forbidden sink?), security automata (does…from github.com

• 
  Deep Work PlanJun 2026 · deepworkplan.com · ▲114

  Models matter. Context matters more. Give your agent a plan.

• 
  Aviator Agents2025 · aviator.co · ▲97

  When we asked developers from large engineering teams, almost everyone is using Claude Code, Cursor, or Copilot. But adoption is still inconsistent. Some of us would have 15 agents running in Claude Code at the same time; some would still refuse to use any of them and write code manually. There's a fragmented AI development problem: - Five developers building similar features, and all of them start from scratch - No way to share "here's how we prompt AI to follow our architecture" - No trail of how the AI changes were generated - People leave the company, so does the their knowledge Aviator…

• 
  Epismo Agent PackageApr 2026 · epismo.ai · ▲106

  Hi HN, I’m Hiroki, founder of Epismo. Every day, people share “must-use” prompts, but copying a single prompt rarely reproduces real outcomes. The missing piece is the workflow: task decomposition, step order, intermediate artifacts, and quality checks. So I built Workflow Hub, an open library of human-AI workflows you can clone and run. Each workflow includes step definitions, inputs, expected artifacts/outputs, and verification checks, so you can copy the whole process, not just a prompt. You can clone a workflow, customize it, then execute it in Epismo with the best agent for each…

• 
  20+ Claude Code agents coordinating on real work (open source)Feb 2026 · github.com · ▲53

  Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…

• 
  Meta-agent: self-improving agent harnesses from live tracesApr 2026 · github.com · ▲14

  We built meta-agent: an open-source library that automatically and continuously improves agent harnesses from production traces. Point it at an existing agent, a stream of unlabeled production traces, and a small labeled holdout set. An LLM judge scores unlabeled production traces as they stream. A proposer reads failed traces and writes one targeted harness update at a time, such as changes to prompts, hooks, tools, or subagents. The update is kept only if it improves holdout accuracy. On tau-bench v3 airline, meta-agent improved holdout accuracy from 67% to 87%. We open-sourced meta-agent.…

• 
  Agentic coding workflows built on Git worktrees and task evidenceJun 2026 · github.com · ▲10

  Autonomous multi-agent orchestration engine for software repos — L0/L1/L2 agents, leases, gates, audits, git-worktree isolation. Detached dispatch by default. GPL-3.0. - alex-reysa/singular-lite

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 18d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 30d ago · world.pixverse.video

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 4d ago · beam.win

• 
  Brila▲1,364

  One-page websites from real Google Maps reviews

  AI · Apr 2026 · brila.ai

• AG
  A game where you build a GPU▲964

  Thought the resources for GPU arch were lacking, so here we are

  Life & fun · Apr 2026 · jaso1024.com

• 
  I built a tiny LLM to demystify how language models work▲915

  Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

  AI · Apr 2026 · github.com

• 
  Fathom 3.0▲800

  AI meeting notes: now bot-free, in ChatGPT & Claude + more

  AI · Apr 2026 · fathom.ai

• 
  Brutalist Concrete Laptop Stand (2024)▲786

  I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay

  Life & fun · Apr 2026 · sam-burns.com

• 
  I built a frontpage for personal blogs▲783

  With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

  AI · Apr 2026 · text.blogosphere.app