Alternatives
Products that do what GSL Solver does
Deterministic VRP Solver for Enterprise Logistics
- 1
- 2
- 3
- 4
- 5AM
When searching on the internet for these type of apps, I didn't find many that were open-source AND easy to use. A lot of them had complicated interfaces, although they had loads of features as well. So what I had in mind when making Stack Solver was an app with a modern interface that has the most essential features. It is also well integrated with Microsoft Excel and renders a 3D customizable drawing. Stack Solver is programmed in C# using the WPF framework to ensure it is fast and light. The interface is built using WPF UI, a library that allows it to keep up with modern trends…
2024 · github.com
- 6TV
May 2026 · github.com
- 7
- 8TB
After training calculator agent via RL, I really wanted to go bigger! So I built RL infrastructure for training long-horizon terminal/coding agents that scales from 2x A100s to 32x H100s (~$1M worth of compute!) Without any training, my 32B agent hit #19 on Terminal-Bench leaderboard, beating Stanford's Terminus-Qwen3-235B-A22! With training... well, too expensive, but I bet the results would be good! *What I did*: - Created a Claude Code-inspired agent (system msg + tools) - Built Docker-isolated GRPO training where each rollout gets its own container - Developed a multi-agent…
2025 · github.com
- 9GO
LLMs are better at being the "mouth" than the "brain" and I can prove it mathematically. I built a deterministic graph engine that offloads reasoning from the LLM. It reduces token usage by 89% and makes a tiny 0.8B model trace enterprise execution paths flawlessly. Here is the white paper and the reproducible benchmark.
Mar 2026 · github.com
- 102C
Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
Feb 2026 · github.com
- 11P3
2019 · github.com
- 12SA
2021 · sparel.app
- 13ID
2024 · nest2d.online
- 14PD
2015 · github.com
- 15AP
2017 · github.com
- 16OS
Everyone saw the AlphaEvolve hype. I got obsessed with how it might work under the hood and decided to just build it myself. My setup uses GPT-4.1 to mutate matrix multiplication code, guided by a bunch of hand-crafted mutation strategies (loop reordering, tiling, Strassen, etc.). Each candidate is evaluated on both speed and accuracy. Then I apply Pareto selection with crowding distance to evolve better ones over generations. I ran into all the usual LLM reward hacks-returning the input, calling np.dot, etc. So I forced primitive-only implementations and tightly constrained the mutation…
2025
- 17AO
Hi, We are building an open-source framework for loading and structuring LLM context to create accurate and explainable LLM answers using knowledge graphs and vector stores. We built the tool with four main concepts in mind: 1. Loader -> uses dlt in the backend to load and structure the data 2. Cognify step -> creates a graph with summaries, labels and factoids that are interconnected across the documents and stored as a representation in the vector store 3. Optimizer -> Uses DSPy to optimize LLM queries, and we plan to extend it to most of the knobs we can turn, like chunking etc. 4. Search…
2024 · github.com
- 18RB
We built HALO (Hierarchal Agent Loop Optimizer), an open-source tool for debugging and optimizing AI agents using their execution traces. It’s a loop. Run your agent, feed the traces to HALO, get the report, apply the fixes, then re-run your agent. HALO takes in OTEL compliant traces from AI agents using tracing frameworks such as Langfuse, Arize/OpenInference, or even just plain JSONL. It uses an RLM (Recursive Language Model) to more efficiently break trace analysis into smaller subproblems in order to find recurring patterns across large amounts of data and fix systemic issues that…
Jun 2026 · github.com
- 19MI
The release of microgpt by Andrej Karpathy is a foundational moment for AI transparency. In exactly 243 lines of pure, dependency-free Python, Karpathy has implemented the complete GPT algorithm from scratch. As a PhD scholar investigating AI and Blockchain, I see this as the ultimate tool for moving beyond the "black box" narrative of Large Language Models (LLMs). The Architecture of Simplicity Unlike modern frameworks that hide complexity behind optimized CUDA kernels, microgpt exposes the raw mathematical machinery. The code implements: The Autograd Engine: A custom Value class that…
Feb 2026
- 20CW
2015 · cadwolf.com
- 21
- 22PI
OP here. Most Deep Learning approaches for TSP rely on pre-training with large-scale datasets. I wanted to see if a solver could learn "on the fly" for a specific instance without any priors from other problems. I built a solver using PPO that learns from scratch per instance. It achieved a 1.66% gap on TSPLIB d1291 in about 5.6 hours on a single A100. The Core Idea: My hypothesis was that while optimal solutions are mostly composed of 'minimum edges' (nearest neighbors), the actual difficulty comes from a small number of 'exception edges' outside of that local scope. Instead of…
Dec 2025
- 23SC
Jun 2026 · github.com
- 24
Free multi-stop route optimizer with time windows
Jul 2026 · routing.kindoflost.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →