Skip to content
View Fosowl's full-sized avatar
658 followers · 41 following

Sponsors

@em-winterschon
@Proxy-Network-RS

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Sharkx3Achievement: YOLOAchievement: Starstruckx4Achievement: QuickdrawAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Sharkx3Achievement: YOLOAchievement: Starstruckx4Achievement: QuickdrawAchievement: Arctic Code Vault Contributor

Highlights

  • Pro

Organizations

@HolobiomicsLab

Block or report Fosowl

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Fosowl/README.md

👋 I am Martin from France, Epitech graduate, also studied at FCU (逢甲大學).

I have interest in AI for Science ; Making Agents go local ; RSI

Current work:

🌼 Mimosa-AI An AI-scientist that learn to evolve multi-agents workflow to perform scientific tasks.

Featured projects:

🐋 AgenticSeek A fully local alternative to Manus AI and other cloud-tied agents.

🐟 3Toks A blazing fast Local Agent. Minimize tokens-per-action to perform agentic tasks faster on Local LLM.

🚘 monocularSlam Simultaneous Localization and Mapping (SLAM) with monocular camera input. Real-time 3D world reconstruction from car dashcam footage. Inspired by Geohot Twitchslam.

🎧 SoundGan A full pipeline for training GANs (Generative Adversarial Networks) to generate audio. from dataset download to training. (kinda broken, will fix)

🎮 ReinforcementLearningGym Solutions to classic OpenAI Gym environments using reinforcement learning. Watch agents learn to walk one episode at a time. Then get stuck with exploding gradients (I am still a noob with rl).

I hope my efforts help make AI more accessible to everyone.

Contact:

Reach out at: martin.legrand@epitech.eu

Popular repositories Loading

  1. agenticSeek agenticSeek Public

    Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

    Python 27.2k 3k

  2. monocularSlam monocularSlam Public

    monocular SLAM implementation, take a camera feed and reconstruct the scene in 3D.

    Python 34 10

  3. SoundGan SoundGan Public

    A project for using Generative adversarial networks to generate any kind of sounds.

    Python 10 3

  4. 3toks 3toks Public

    Extremely fast & token-frugal agentic framework for small or hardware constrained LLMs. Run agents in a cave with a box of scrap. 3 Tokens per action or bust!.

    Python 10 3

  5. S.T.A.R.S.E.T-Game-Engine S.T.A.R.S.E.T-Game-Engine Public

    2D Game engine made in C.

    C 7 2

  6. CircuitSimulator CircuitSimulator Public

    C++ Circuit simulator.

    C++ 5 2