Alternatives
Products that do what Tinker does
Control every aspect of model training and fine-tuning
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9NO
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
- 10
- 11
LLM reinforcement fine-tuning platform to improve LLM output
2025
- 12
- 13
- 14
- 15
- 16SM
Hello HN, I built Syna to understand how modern ML frameworks like PyTorch actually work — from the ground up. It’s a minimal, define-by-run (dynamic graph) framework inspired by DeZero, written entirely with NumPy. Unlike most libraries, Syna includes a basic reinforcement learning module right inside the same framework — no separate packages. It’s not about speed or GPUs — it’s about clarity, simplicity, and learning the internals of machine learning. Great for students, educators, and anyone curious about what’s really happening under the hood. GitHub:…
Oct 2025 · github.com
- 17
Zero-config hosting to launch specialized AI teams instantly
Feb 2026
- 18UA
Hey HN! After using a combination of Unsloth and Axolotl a lot, and finding it generally painful to figure out the right performance tuning for things like batch sizing and multi-GPU sharding, I wrote a small Python lib that sets up known-good LoRA training configurations for Llama 3.1 8B and 70B Instruct, and includes helpers for distilling from larger models or training on serverless finetuning platforms, and includes a walkthrough for distilling DeepSeek-R1 into a Llama 3.1 8B LoRA... But you can use it for pretty much any finetuning task, not just distilling large models!
2025 · github.com
- 19SC
Unlike LoRA and its variants, which inject trainable parameters directly into the weights of the Transformer, requiring tight coupling with the backbone. ShadowPEFT instead enhances the frozen large base model by adding a lightweight, centralized, pretrainable, and detachable Shadow network. This shadow network operates in parallel with the base model, delivering learned corrections to each decoder layer. Because the shadow module is architecturally decoupled from the backbone, it can be independently trained, stored, and deployed, benefiting edge computing scenarios and edge-cloud…
Apr 2026 · github.com
- 20AC
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
- 21SG
Hi HN, I built NOMA (Neural-Oriented Machine Architecture), a systems language where reverse-mode autodiff is a compiler pass (lowered to LLVM IR). My goal is to treat model parameters as explicit, growable memory buffers. Since NOMA compiles to standalone native binaries (no Python runtime), it allows using realloc on weights mid-training. This makes "self-growing" architectures a system primitive rather than a complex framework hack. I just pushed a reproducible benchmark (Self-Growing XOR) to validate the methodology: it compares NOMA against PyTorch and C++, specifically testing how…
Dec 2025 · github.com
- 22AO
I've built an airgapped Retrieval-Augmented Generation (RAG) system for question-answering on documents, running entirely offline with local inference. Using Llama 3, Mistral, and Gemini, this setup allows secure, private NLP on your own machine. Perfect for researchers, data scientists, and developers who need to process sensitive data without cloud dependencies. Built with Llama C++, LangChain, and Streamlit, it supports quantized models and provides a sleek UI for document processing. Check it out, contribute, or suggest new features!
2024 · github.com
- 23RA
We built RapidFire AI, an open-source Python tool to speed up LLM fine-tuning and post-training with a powerful level of control not found in most tools: Stop, resume, clone-modify and warm-start configs on the fly—so you can branch experiments while they’re running instead of starting from scratch or running one after another. - Works within your OSS stack: PyTorch, HuggingFace TRL/PEFT), MLflow. - Hyperparallel search: launch as many configs as you want together, even on a single GPU - Dynamic real-time control: stop laggards, resume them later to revisit, branch promising configs in…
Sep 2025 · github.com
- 24AP
I'm Guy, the founder behind Snyk — now building Tessl, a package manager for agent skills. We’ve recently witnessed that most teams still treat skills as static artifacts: markdown files, created or copied from repo to repo. This approach offers a strong initial boost, but quickly creates debt: - Skills are duplicated, and updates never roll out. - Poor quality skills go unseen, misguiding agents instead of helping. - Skill knowledge grows stale, and don’t keep up with the systems and practices they describe. Without a way to evaluate skills, teams have no clear way to understand how good a…
Feb 2026 · tessl.io
Ranked by how close each launch is in meaning, then by votes. Refine with a description →