Alternatives
Products that do what acorn – LLM framework for long running agents does
Hi HN, This is Andrei from askmanu and I'm super happy to share a new framework I've been working on: acorn. It takes all the best parts of DSPy, langchaing, instructor, etc and wraps it in a beautiful and easy to use API. Very easy to define model I/O, branches, define callbacks for every step, etc See the getting started docs here: https://github.com/askmanu/acorn/blob/main/docs/getting-star... Try out the different demos here: https://huggingface.co/spaces/askmanu/acorn
- 1NO
Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
2024 · github.com
- 2NL
Built this because I was tired of every AI tool shipping my data to someone else server n0x runs the full stack LLM inference via WebGPU, autonomous ReAct agents, RAG over your own docs, sandboxed Python execution via Pyodide all inside a single browser tab. No account No keys No backend Models download once, cache in IndexedDB permanently. Biggest challenge was context window budgeting for the agent loop and making the WASM vector search non-blocking. Happy to talk architecture. GitHub: https://github.com/ixchio/n0x | Live demo: https://n0x-three.vercel.app
Mar 2026 · n0xth.vercel.app
- 3IS
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
- 4A1
I've seen a lot of comments about how complex frameworks like LangChain can be. Over the holidays, I wanted to see how minimal an LLM framework could get if we stripped away everything non-essential. The result is an LLM framework in just 100 lines of code. These 100 lines capture what I see as the core abstraction of most LLM frameworks: a nested directed graph that breaks down tasks into multiple LLM steps, with branching and recursion to enable agent-like decision-making. From there, you can layer on more advanced features like agents, RAG, task decomposition, and more. I’ve intentionally…
2025 · github.com
- 5LP
I was not getting good cache utilization when including dynamic context in agent threads. After a lot of experimentation, I found a good pattern that minimizes how often long lived conversation history gets modified while still supporting dynamic context. It has flexible hooks for doing things like truncating or summarizing tool outputs when transitioning messages to the long term history. And I'm seeing >>90% of tokens hitting the cache for my agents despite including a lot of dynamic user context. There are a wide range of agent prompting strategies so I'd love to hear where this library…
Jun 2026 · github.com
- 6WB
Here is a production-first Keras-inspired LM framework, built with the advice of François Chollet (ex-Google, creator of Keras and ARC-AGI), our technical advisor. This system have already been deployed in production with our clients (which is why we have already every LLMOps practice implemented). It is also compatible with Jupyter and Marimo to integrate seamlessly in you Data Scientists workflows. You can try the code examples online on HF space and you can find more information in the documentation and FAQ. If you have any feedback for us don't hesitate to join our discord! More releases…
2025 · github.com
- 7CR
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
- 8PE
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
- 9
Around 3 months ago, we were thinking why none of the iPhone apps running an LLM are built as a full harness (as in inference + agentic loop + context management + tools + MCP servers and etc.). It became more interesting when we noticed even the new Siri is not fully on device (and not available in EU for that matter). Having built a few agentic products around a custom harness in the past, we thought this shouldn't be that hard. well, we underestimated how "dumb" a 4B model can be, especially when it comes to tool calling. :D We tried 8 different models and we settled on Qwen 3.5 4B and we…
18d ago · orvena.app
- 10UL
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
- 11UA
I've been using LLMs for long discovery and research chats (papers, repos, best practices), then distilling that into phased markdown (build plan + tests), then handing those phases to Codex/Claude to implement and test phase by phase. The annoying part was always the distillation and keeping docs and architecture current, so I built Unpack: a lightweight GitHub template plus docs structure and a few commands that turns conversations into phases/specs and keeps project docs up to date as the agent builds. It can also generate Mintlify-friendly end-user docs. There are other…
Feb 2026 · github.com
- 12AG
I’ve been building LLM tooling for a small VC fund and found myself explaining the same mental model over and over to non-technical people around me: how a stateless LLM becomes a chatbot, how tool use works, what an agent is mechanically, and why context windows shape all of it. I never found a guide that covered that full chain at the level I wanted, so I wrote one. It’s nine short chapters, each building on the last. Deliberately simplified: the goal is a useful mental model, not a textbook. Feedback, corrections, and contributions welcome: github.com/ymyke/aiaiai
Apr 2026 · aiaiai.guide
- 13IB
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
- 14CA
TL;DR: we built a framework-agnostic agent runtime that uses gVisor for isolation and runs on k8s. It’s open-source under AGPLv3 Recently we’ve been working on a customer support “AI assistant” - essentially an interactive knowledge base/L1 support but with an option to touch resources that belong to a customer it’s talking to. We found existing tools to be lacking in these aspects: 1. Fully intercepted i/o. We wanted to trace out LLM calls as well as any other networking calls attempted by the harness so that guardrails and audit trails apply to all current and future systems…
Jul 2026 · github.com
- 15CP
Hi HN! I've never posted anything on here before, but this project was too fun to pass up. I've been learning a lot about agents lately, and wanted to see if I could replicate some of the results of Windsurf and Cursor. Generally I love these tools, but when you're stuck behind an "enterprise" firewall, they don't work as well. This sad state of affairs motivated me to understand SWE agents more. Does it work? Yes. Is it as good as Cursor and Windsurf? Not quite, but it's pretty darn close, depending on the model you use. I'm lacking a few features like semantic indexing, MCP support, but…
2025 · github.com
- 16RA
Hi there, looking for feedback on my new project "Featherless.AI" The idea is to allow users to run all the models on hugging face instantly. Via the OpenAI API compatible endpoint. Why? Because its a real chore to download models and spin up GPUs, especially if you want to test multiple models. Not to mention GPUs cost multiple dollars an hour to rent. And if we want more people to use open source AI, we got to make it easier for them to try and play with all of them. So what if instead of spinning up dedicated GPUs per model (which is what every provider is doing) We can startup a LLM…
2024 · featherless.ai
- 17NT
I built a CLI tool that turns codebases and PRs into diagrams so you can quickly understand how things fit together. Originally made it because I couldn't follow my own AI-generated repos. Just shipped a big update: - Switched from D2 to Mermaid for rendering - Tree-sitter AST parsing + agentic flow instead of raw LLM calls. ~50x faster. - Works on any GitHub repo or PR, not just local - Dropped the web frontend, it's just a CLI now - Published as a pip package Still a ton to improve and I'm building fast. Feedback, issues, PRs all welcome.
Feb 2026 · github.com
- 18GB
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
- 19LA
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
- 20AA
We’ve published a set of open-source reference implementations on how to build production-grade Agentic AI applications on AWS. What’s in the repo: • Agentic RAG, memory, and planning workflows with LangGraph & CrewAI • Strands-based flows with observability using OTEL & Arize • Evaluation with LLM-as-judge and cost/performance regressions • Built with Bedrock, S3, Step Functions, and more GitHub: https://github.com/aws-samples/sample-agentic-frameworks-on-... Would love your thoughts — feedback, issues, and stars welcome!
2025 · github.com
- 21MA
Hey HN! I built a thing and I'm really excited to share it. EDIT: I meant to link to the github, not the website: https://github.com/max-hq/max Like many of us here, I've been commonly reaching for a pattern of "pull data into db; give it to claude" for a while, whilst doing data spelunking or building tooling - for the same reasons mentioned by thellimist over here [1] and a few other recent "CLI vs MCP" posts. To that end, about a month ago I started building a project called `max` - its goal is to cut the middleman and schematise any data source for you. Essentially,…
Mar 2026 · max.cloud
- 22HF
We have a massive GPU cluster and developed our own infrastructure to manage the cluster and train massive models. There's how it works: 1. You upload the dataset with preconfigured format into HuggingFaсe [1]. 2. Choose your LLM (e.g. LLaMa 70B, Mistral 7B) 3. Place your submission into the queue 4. Wait for it to get trained. 5. Then you get your trained model there on HuggingFace. Essentially, why would we want to do it? 1. We already have an experience with training big LLMs. 2. We could achieve near-perfect infrastructure performance for training. 3. Sometimes GPUs have just nothing to…
2023 · higgsfield.xyz
- 23MA
Hi HN, A couple weeks ago I shared an early version of a side project I’ve been tinkering with called Persistent Mind Model. I built it at home on an i7-10700K / 32GB RAM / RTX 3080 because I was curious whether an AI could keep a stable “mind” over time, that could "think" about it's own identity as an LLM, instead of resetting every session. After a lot more tinkering, I think the architecture is finally in a solid place. Basically, it saves everything the AI does, thoughts, decisions, updates as a chain of events in a local SQLite database. Because the “identity” is stored in…
Nov 2025 · github.com
- 24CA
Hi HN, I've been working with LLMs in production for a while both as a solo dev building apps for clients and working at an AI startup. The one thing that always was a pain was to pay OpenAI/Gemini/Anthropic a few dollars a month just for me to say "test" or have a CI runner validate some UI code. So I built this server called ChunkBack, that mocks the popular llm provider's functionality but allows you to type in a deterministic language: `SAY "cheese"` or `TOOLCALL "tool_name" {} "tool response"` I've had to work in some test environments and give good results for experimenting…
Nov 2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →