I made a local proxy for AI tool calls to keep my API keys safe

What it does

Define tools, compose workflows, test and run them. MCP servers, REST APIs, and CLI commands in one config, one UI, one audit log. Factorly is a local runtime for agent tool chains. It manages tool calls, injects credentials from an encrypted vault, enforces governance rules, and logs everything. Your agent sees workflows, tools, and data. It never receives your credentials, only the tool's response. Secrets stay secret. brew install factorly-dev/tap/factorly # or: npm install -g factorly # or: pip install factorly # or: go install github.com/factorly-dev/factorly@latest Quick Start Zero config: wrap any existing MCP server and it's instantly callable through Factorly: # 1. Create a project…from github.com

• 
  AgentlyJul 2026 · agently.dev · ▲336

  Agently is an AI Work OS where documents, tasks, team chat, and integrations are fully interconnected, and AI employees operate inside that shared workspace. Instead of prompting AI in isolation, agents can read project context, turn strategy docs into tasks, coordinate with teammates, run research/outreach/content workflows, update boards, and push results back into the system or external tools. The workspace acts as persistent memory, so work continues instead of resetting every prompt. Happy to answer any questions

• 
  RuntimeMay 2026 · runtm.com · ▲299

  Sandboxed coding agents for everyone on your team

• 
  LatchkeyMar 2026 · github.com · ▲122

  Hi HN, At Imbue, we’ve been following the rapid developments in the agent landscape and noticed that the way agents interact with third-party services on users’ behalf often leaves a lot to be desired. Integrations are ad hoc, complicated, context-heavy, and either unfriendly to non-technical users or tied to a lock-in of some sort. We‘re experimenting with a command-line tool, Latchkey, that could be used by local agents targeted at non-technical users while avoiding remote intermediaries. As far as we know, this is the only existing approach at the intersection of these two goals. Core…

• 
  KastraJul 2026 · kastra.ai · ▲332

  Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. We built this product to control pre- and post-inference workloads. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. Kastra pushes an allow, hold, and deny decision before the action runs. You can build these policies in plain English from the web app. The interception engine evaluates the tools, targets, and parameters of every action at sub 1ms at a scale of billions of interceptions per day. We also…

• 
  Donely Mar 2026 · donely.ai · ▲220

  Hey HN, I'm Harsha, founder of Donely (https://donely.ai). What is Donely? Donely is an AI agent that lives on your Mac. It sees your screen, detects tasks in real-time, and autonomously executes them using your apps—think Jarvis for macOS. It monitors your workflow, answers questions with full context, and completes tasks with one-click approvals. The New Feature: Remote Computer Use Today we're shipping remote access. You can now control your Donely-powered Mac from anywhere through our web app. Whether you're traveling or away from your desk, you can kick off automation tasks on…

• 
  TermlyNov 2025 · termly.dev · ▲82

  Hey HN! I'm one of the developers of Termly. Problem: I love using Claude Code for development, but being chained to my laptop all day wasn't working. SSH + terminal emulators felt clunky for interactive AI coding sessions. Solution: Built a WebSocket relay that mirrors your AI coding session to mobile with zero-knowledge E2E encryption. How it works: 1. npm install -g @termly-dev/cli 2. termly start (wraps your AI tool) 3. Scan QR code with mobile app 4. Your session syncs in real-time, encrypted end-to-end Tech stack: • Open source CLI (MIT licensed) - inspect the code yourself •…

• 
  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

• 
  Beam.win▲378

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

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• 
  Brew ▲900

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲896

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲806

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲795

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• 
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

  Life & fun · May 2026 · github.com

• 
  Files.md – Open-source alternative to Obsidian▲730

  🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md

  Dev tools · May 2026 · github.com