Alternatives
Products that do what Attach Gateway – one-command OIDC/DID auth for local LLMs does
We’ve been building local and on-prem agent workflows for open-source LLMs. Engines like Ollama or vLLM ship with no auth, so every team ends up writing the same JWT proxy. Attach Gateway is a single process that sits in front of any model server and handles the boring bits: - verifies OIDC / DID JWTs - adds X-Attach-User and X-Attach-Session headers so downstream agents share the same identity - optional /a2a/tasks/send endpoint for Google-style A2A hand-offs - mirrors prompts + completions to Weaviate (runs in Docker) One `pip install attach-dev`, export a token, run…
- 1
- 2
- 3
- 4
- 5
- 6
- 7OS
Hi HN, Matvey, Ildar, Joey, and Dominik here. If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools. We were too, and found that solutions like prompt-based filtering or secondary "guard" LLMs can be unreliable. Our thesis is that agent security should be handled at the network level between the agent and the LLM, just like a traditional web application firewall. So we built Archestra Platform: an open-source gateway that acts as a secure proxy for your AI agents. It's designed to be a deterministic firewall against…
Oct 2025 · archestra.ai
- 8AG
Hi HN My name is Salman and I work on Arch GW - the intelligent gateway designed to protect, observe, and personalize LLM applications with your APIs. https://github.com/katanemo/arch Our team built Envoy Proxy at Lyft, and re-imagined it with the belief that: Prompts are nuanced and opaque user requests, which require the same capabilities as traditional HTTP requests including secure handling, intelligent routing, robust observability, and integration with backend (API) systems for personalization – all outside business logic. Engineered with purpose-built LLMs, Arch…
2024 · docs.archgw.com
- 9HA
Demo starts at 50m into the video. This was a bit terrifying to record because 2am the previous night everything was totally broken after a major refactor (so that we could add external LLM support as well as local GPUs). But pressure can be a useful force :-D We start with a stack deployed on my laptop without a GPU, pointing to together.ai so we can run open source LLMs easily without having to have access to a GPU. We show simple inference through the ChatGPT-like web interface (with users, sessions etc) and then simple drag'n'drop RAG. Then we show some helix apps defined as yaml: Marvin…
2024 · youtube.com
- 10MA
Hey HNers - Riz here. I got together with a few guys and we built an LLM gateway. It's designed for small teams working on early-stage products, and can be deployed to AWS using a single command (i.e. `mantis deploy`). It's self-hosted, and is designed to belong to you.
Jun 2026 · github.com
- 11IB
Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…
Jan 2026 · github.com
- 12
- 13PE
Hey HN — I’m Adil from Katanemo (with Salman, Shuguang, and Meiyu) We previously shared an early version of this project as ArchGW. Based on customer feedback, the scope expanded from “LLM routing and model access” into something broader: delivery infrastructure for agentic applications. We renamed it to Plano and reworked the architecture accordingly. The problem On-the-ground AI practitioners will tell you that calling an LLM is not the hard part. The really hard part is delivering agentic applications to production quickly and reliably, then iterating without rewriting system code every…
Jan 2026 · github.com
- 14AC
There's LLM Council and similar tools, but they use predefined model lineups. This one is different in a few ways that mattered to me: *Bring your own models.* Mix Ollama (local), OpenAI, Anthropic, Groq, Google — or any OpenAI-compatible endpoint — in whatever combination you want. A council of DeepSeek-R1 + llama2-uncensored + mistral-nemo is a very different deliberation than GPT-4o + Claude + Gemini. *Zero server, zero account, zero storage.* The app is purely static. API calls go directly from your browser to providers. Nothing touches a backend. No tokens, no sessions, no analytics.…
Feb 2026 · github.com
- 15TO
I built DevClaw, an OpenClaw plugin that turns each Telegram group into an isolated, autonomous dev team: planner/orchestrator, DEVs, and QA all running on their own. I use it for all my development now. Issues on GitLab/GitHub are the single source of truth, and three things compound to save around 70% on tokens: model tiering (Haiku for typos, Opus for architecture), session reuse across tasks, and token-free scheduling that burns zero LLM calls for orchestration. Please try it and give some feedback. Also keen to hear from anyone running autonomous coding agents, especially what…
Feb 2026 · github.com
- 16AS
MachineAuth is a self-hosted OAuth 2.0 server for authenticating AI agents and machines. What is an AI agent in this context? A software bot (like OpenCLAW, Claude Code, etc.) that makes API calls to access protected resources. Instead of sharing long-lived API keys, your agents can authenticate using OAuth 2.0 Client Credentials and receive short-lived JWT tokens. Why? No more sharing API keys Short-lived tokens (configurable) Easy credential rotation Industry-standard security
Feb 2026 · github.com
- 17
- 18KD
Every AI agent that does something useful - opening a PR, posting in Slack, updating a ticket - needs to call an API on behalf of a user. That means OAuth. Authorization flows, token storage, refresh logic, per-user credential isolation. Today, most teams solve this with a long-lived API key in an .env file, shared across every user and every session. As everyone in an organization becomes a software engineer - whether they know it or not - you can't expect each of them to roll their own OAuth. Secure credential handling needs to be baked into the infrastructure. The core issue: agents are a…
Mar 2026 · kontext.dev
- 19AC
Hi HN! We love the "backend-less" stack: Stripe for payments, Supabase for data, Clerk for auth. But the moment we add AI features, we're forced to spin up a backend to hide API keys, implement per-user token-based rate limits and graceful degradation, etc. So we built Airbolt. What it does: Drop in our SDK and start making OpenAI calls directly from your frontend. Your keys are AES-256-GCM encrypted on our servers, never exposed to the client. We provide token-based per-user rate limits and origin allow lists to address inference abuse. Short-lived JWTs and bring-your-own-auth are coming…
Sep 2025 · airbolt.ai
- 20
Contain LiteLLM, Bifrost, Portkey.. behind one control plane
14d ago · agnos-llm-gateway.site
- 21IS
Hey HN! For that last 8 months I've been trying to make agents that can hack web applications to find vulnerabilities in them - An AI Security Tester. The system has 29 agents in total, a custom LLM Orchestration framework which works on the task-subtask architecture (old-school but works amazingly for my use case, and is pretty reliable) with custom agent calling mechanism. No Auo-Gen, Langchain and Crew AI - Everything custom built for pentesting. Each test runs in an isolated Kali linux environment (on AWS Fargate), where the agents have full access to the environment to undertake any…
2025
- 22LA
LunaRoute is a high-performance local proxy for AI coding assistants like Claude Code, OpenAI Codex CLI, and OpenCode. Get complete visibility into every LLM interaction with zero-overhead passthrough, comprehensive session recording, and powerful debugging capabilities. - See Everything Your AI Does - get full logs (JSONL), summary of sessions including tokens used (input/output) as well as tools usage and success rates. - Privacy & Compliance Built-In - redact or tokenize any sensitive information (regex based). - Speaks OpenAI and Anthropic dialects so you can route (and translate)…
Oct 2025 · github.com
- 23LC
Hey, folks here is a peek into Jujutsu. We at Poozle are working with hundreds of APIs and it has been always frustrating to 1. Search the API in the documentation or ask ChatGPT 2. Then copy it to the postman and understand/test the API 3. Generate code to integrate into the codebase We thought how about having all of this at one place. We currently fine-tuned LLM on public REST APIs to reduce hallucination and then combined it with ChatGPT and Postman. I look forward to feedback, feature requests and discussions!
2023 · loom.com
- 24IB
hey hn, I built an open-source Perplexity clone that can run local LLMs and cloud LLMs. It's fully self-hostable through Docker and uses ollama to support local LLMs. The demo video in the repository shows me running it locally with llama3 on my M1 Macbook Pro. I'm open to any suggestions or feedback, thanks!
2024 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →