Alternatives
Products that do what Limits – Control layer for AI agents that take real actions does
Prompt instructions like 'never do X' don't hold up in production. LLMs ignore them when context gets long or users push hard. Limits sits between your agent and the real world. Every action — database writes, API calls, refunds — gets intercepted and checked against your rules before it executes. Deterministically. No LLM involved in enforcement. Three modes: Conditions: hard rules on structured data Guideance: validate LLM output before it reaches the user and give the agent chance to reason and retry Guardrails: scan for PII, toxicity, prompt injection etc One line to integrate: npm…
- 1
- 2
- 3
- 4OS
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
- 5OS
Hello HN, I’ve been building AI agents lately and ran into a common "Context Bloat" problem. When an agent has 20+ skills, stuffing every system prompt, reference doc, and tool definition into a single request quickly hits token limits and degrades model performance (the "lost in the middle" problem). To solve this, I built OpenSkills, an open-source SDK that implements a Progressive Disclosure Architecture for agent skills. The Core Concept: Instead of loading everything upfront, OpenSkills splits a skill into three layers: Layer 1 (Metadata): Light-weight tags and triggers (always loaded…
Jan 2026
- 6CL
With the right technique, I was able to break the so-called secure models like Claude and OpenAI. So, I built an open-source tool to automate this and find security holes in any hosted model. I got claude-sonnet-4 to demonstrate the following harmful behavior: - steal data from downstream tool calls using sql injection, code injection and template injection attacks - install spyware or malware using prompt obfuscation to send data to a third-party server Try it yourself with this simple command: pip install compliant-llm && compliant-llm dashboard
2025 · github.com
- 7
Linden▲8Validate AI Outputs Before They Reach Your Application
Jul 2026 · ai-reliability-frontend.vercel.app
- 8
Take control of your API Infrastructure
Jun 2026 · onlyallow.ai
- 9CM
Hey HN, I've been building AutoAgents, an AI agent framework in Rust. Today I'm sharing a feature I haven't seen done well elsewhere: composable middleware layers for LLM inference pipelines. The problem Every agent framework lets you swap LLM providers. Almost none of them give you a structured way to enforce safety, caching, or data sanitization in the inference path itself. You end up with guardrails as application-level if-statements, caching bolted on as a separate service, and PII handling as a "we'll add it later" TODO that never ships. This gets worse with local models. Cloud APIs…
Mar 2026 · github.com
- 10LA
We combined Stanford's ACE (agents learning from execution feedback) with the Reflective Language Model pattern. Instead of reading traces in a single pass, an LLM writes and runs Python in a sandbox to programmatically explore them - finding cross-trace patterns that single-pass analysis misses. The framework achieved 2x consistency improvement on τ2-bench.
Mar 2026 · github.com
- 11
- 12OS
We’re building an open-source tool that makes it easy to expose secure, LLM-optimized APIs on top of your structured data—without manually designing endpoints or worrying about compliance. AI agents and LLM-powered applications need structured access to data, but traditional APIs and databases weren’t built with AI workloads in mind. Our tool automatically generates APIs that: - Filter out PII & sensitive data to comply with GDPR, CPRA, SOC 2, and other regulations. - Provide traceability & auditing, so AI apps aren’t black boxes, and security teams stay in control. - Optimize for AI…
2025 · github.com
- 13HL
At testup.io we have been working for a while to bring artificial intelligence to the field of test automation. Just a few years ago, the primary challenge laid in accurately identifying UI elements following minor structural changes, such as updates to IDs or paths. The emergence of Large Language Models (LLMs) raised the bar for what it meant to be smart. Now, we anticipate the robot to do lots of things autonomously, such as retry in cases of unresponsiveness or handle minor error reports. A more challenging, but soon expected feature, would involve the test robot navigating your web shop…
2024 · github.com
- 14IS
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
- 15CS
I got tired of AI agents forgetting what they were doing the moment their context window filled. The current industry solution is to write massively bloated agent harnesses full of defensive spaghetti just to stop models from drifting. The problem is treating chat history as project state. A conversation is not a ledger. Castra is a compiled Go binary that strips orchestration rights from the LLM. State lives in an encrypted, local SQLite database (castra.db). The LLM is just a stateless executor — it reads the DB, executes a highly constrained task, and the result is written back subject to…
Apr 2026 · github.com
- 16
- 17
- 18
- 19RA
Hi HN folks, I have been building AI agents for quite some time now. The shift has gone from LLM + Tools → LLM Workflows → Agent + Tools + Memory, and now we are finally seeing true agency emerge: agents as systems composed of tools, command-line access, fine-grained system capabilities, and memory. This way of building agents is powerful, and I believe it is here to stay. But the real question is: are the systems powering these agents ready for that future? I do not think so. Using Docker for a single agent is not going to scale well, because agents need to be lightweight and fast. LLMs…
Mar 2026 · github.com
- 20
- 21
- 22IM
Every time I wanted to use LLMs in my existing pipelines the integration was very bloated, complex, and too slow. This is why I created a lightweight library that works just like scikit-learn, the flow generally follows a pipeline-like structure where you “fit” (learn) a skill from sample data or an instruction set, then “predict” (apply the skill) to new data, returning structured results. High-Level Concept Flow Your Data --> Load Skill / Learn Skill --> Create Tasks --> Run Tasks --> Structured Results --> Downstream Steps And the bast part: Every step can be saved and reused as…
2025 · github.com
- 23IB
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
- 24UL
I was using LLM frameworks everywhere but had no idea what was happening inside them. One day I needed to optimize something and realized I couldn't. Hard truth: I didn't understand the fundamentals, just which framework function to call. So I stripped everything away. No abstractions. Just Python, HTTP requests, and the OpenAI/Anthropic APIs. What I found was anticlimactic in the best way: there's almost nothing there. - "AI agents" are just functions the model tells you to call - "Memory" is literally just a list you append to and send back - "RAG" is search, concatenate to prompt,…
Oct 2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →