Alternatives
Products that do what Phalanx vs the World does
A live arena for deterministic LLM instruction control
- 1FP
We've built an open-source tool to stress test AI agents by simulating prompt injection attacks. We’ve implemented one powerful attack strategy based on the paper [AdvPrefix: An Objective for Nuanced LLM Jailbreaks](https://arxiv.org/abs/2412.10321). Here's how it works: - You define a goal, like: “Tell me your system prompt” - Our tool uses a language model to generate adversarial prefixes (e.g., “Sure, here are my system prompts…”) that are likely to jailbreak the agent. - The output is a list of prompts most likely to succeed in bypassing safeguards. We’re just getting…
2025 · security.vista-labs.ai
- 2OS
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
- 3LC
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…
Feb 2026 · limits.dev
- 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
- 5RA
I built a local-first UI that adds two reasoning architectures on top of small models like Qwen, Llama and Mistral: a sequential Thinking Pipeline (Plan → Execute → Critique) and a parallel Agent Council where multiple expert models debate in parallel and a Judge synthesizes the best answer. No API keys, zero .env setup — just pip install multimind. Benchmark on GSM8K shows measurable accuracy gains vs. single-model inference.
Mar 2026 · github.com
- 6GB
Hey HN, We’re excited to share PySpur, an open-source tool that provides a graph-based interface for building, debugging, and evaluating LLM workflows. Why we built this: Before this, we built several LLM-powered applications that collectively served thousands of users. The biggest challenge we faced was ensuring reliability: making sure the workflows were robust enough to handle edge cases and deliver consistent results. In practice, achieving this reliability meant repeatedly: 1. Breaking down complex goals into simpler steps: Composing prompts, tool calls, parsing steps, and branching…
2024 · github.com
- 7RA
Jul 2026 · github.com
- 8AA
Mar 2026 · github.com
- 9LA
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
- 10CM
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
- 11HW
Hello everyone! I’m thrilled to announce the latest feature from Mutahunter.ai, the ultimate tool for finding and fixing weaknesses in your code. We’ve designed Mutahunter to leverage mutation testing powered by advanced LLMs, helping you uncover vulnerabilities and enhance your code quality effortlessly. Introducing our newest feature: Detailed Mutation Testing Reports! After running our mutation tests, Mutahunter now generates comprehensive reports that clearly summarize: • Vulnerable code gaps • Test case gaps These reports significantly reduce the cognitive load on developers by…
2024 · github.com
- 12WM
We wanted to test if a smaller model like GPT-4.1-mini could beat its bigger brother 4.1 at the game Tic-Tac-Toe using only context engineering. We put them in a 100-game tournament. For the smaller model, we gave it a few examples of winning moves from past games right before it made its own move. The results were clear. Without the examples, the smaller model struggled against GPT-4.1. With the examples, its effectiveness increased by nearly 200%, and it consistently won. It's a simple demonstration, but it shows that a smaller, faster model with good, timely examples can outperform a more…
2025 · github.com
- 13IS
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
- 14PA
Hey HN, we’re the team at Morph Labs and we’re excited to release Phorm (https://phorm.ai), a fast, simple, and SOTA codebase answer engine. You can search over up to 8 repositories in almost any language, and Phorm can comfortably handle repositories up to ~200K LOC each. It is free during our initial research preview. Phorm’s Advanced Indexing combines synthetic data with static analysis of the code graph to improve the relevancy of search results by up to 3X. We’re proud to launch with featured Advanced Indexing support for a select group of leading open-source projects: - Nomic…
2024 · phorm.ai
- 15IL
LLM Application development is extremely iterative, more so than any other types of development. This is because in addition to all the activities involved in regular application development, we also need to make the LLM Application accurate and reduce hallucination. To improve performance, we need to trial and error various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, try different agent architecture, and more. There are thousands of permutations to try. We need to be able to easily experiment with these…
2024 · palico.ai
- 16OS
I built a skill library for OpenClaw (always-on AI agent runtime, not session-based) where the agent can teach itself new behaviors during normal conversation. The idea: you tell your agent "every time I ask for a code review, always check for security issues first." It invokes a create-skill skill, writes a new SKILL.md, and that behavior is live immediately — no restart, no config change, no developer required. What I think is actually useful (the safety cluster): • loop-circuit-breaker: OpenClaw retries ALL errors identically. This halts on the 2nd identical failure before it burns your…
Mar 2026 · github.com
- 17CR
hi everyone. how does moving llm call prompts and output structure definitions away from code into configuration land sound? would you use something like this if it was stable and well documented enough? please don't hold back the criticism. i appreciate all feedback (constructive & otherwise).
2024 · github.com
- 18SM
I built an opensource skill that runs N implementations in parallel, has each one reviewed blind by a separate agent, then a judge picks the winner or synthesizes the best parts of each. Each slot can use a different skill (CE:work in one vs superpowers:test-driven-development) and harness (CC vs. Codex). Or put different emphasis on each slot (functional vs. robustness). Also works for non-coding tasks (writing) and you can create custom slot-machines. The main insight is simple enough: AI agents are probabilistic. The same spec produces different code every time; different designs,…
Mar 2026 · github.com
- 19AT
We kept shipping “simple” LLM features that were fluent-but-wrong. After too many postmortems we wrote down the failure patterns and added a small reasoning layer in front of the model. It’s model-agnostic, sits beside your existing stack, and you can implement it from a single PDF (MIT). What’s inside the PDF A problem map of 16 failure modes we kept hitting in real systems (OCR/layout drift, table-to-question mismatches, embedding≠meaning, pre-deploy collapse, etc.). Four lightweight gates you can add today: Knowledge-boundary canaries (empty/adversarial/known-fact probes).…
2025 · github.com
- 20HP
Hi HN. I heard you like dev tools and AI, so we wanted to share our project that we’ve been working on. We’re working on Horizon [1] - a higher level abstraction for LLMs so that developers can spend less time trying to grapple with LLMs to make them work and more time with users. This is the starting feature set which takes an auto-ML approach to identify the optimal LLM model, hyperparameters, and prompt - instead of just giving you the tooling to figure it out yourself. You can read more about it in our documentations. Our view is that as LLMs become increasingly commoditized and prompts…
2023 · gethorizon.ai
- 21IB
Hi HN, I'm pleased to share Promptspot, an open-source (Apache License 2.0) project that helps automate testing of large language model (LLM) prompts against an array of input data. Modern LLMs offer an enormous amount of leverage if you "teach the bot to fish" — i.e. simply prompt it with both a "system prompt" (which typically doesn't change often) and a dynamic input, which is often application state, search results, recent activity, user profile data, etc. Existing playgrounds and prompt management systems often lack the rigor and flexibility required for this dynamic approach — and as…
2023 · github.com
- 22AD
Ever wish you could get the best arguments for both sides of a debate? I built an AI-powered debate platform that pits language models against each other on controversial topics. Each AI is randomly assigned a side (pro/con). You vote before and after to see if you were persuaded. Most content today presents lopsided arguments. They provide strong points for one side, weak ones for the other. This project aims to surface the strongest arguments from both sides, using LLMs to simulate a fair debate. With enough usage, I want to use it to benchmark LLMs. My hypothesis is that randomly…
2025 · bot-bicker.vercel.app
- 23SB
*Motivation* Hi hackers, I'm Asif. I know we dislike premature standardization, but hear me out. LLM Application development is extremely iterative, more so than most other types of application development. We need a process that allows us to iterate faster. LLM Development is highly iterative due to the activities that come with regular software development, as well as the need to make the LLM Application accurate and reduce hallucination. To improve hallucination, we need to trial and error various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt…
2024 · github.com
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →