Lists (32)
agent frameworks
awesome lists
awesome lists i want to keep track ofbundled-building-packages
stuff like a ready to go fastapi server + auth, etcdiscord
relevant to discord/redbotexternal-brain
the mech suit but for your brainfren w python to mod
from-papers
repos that have papers associated w them🔮 Future ideas
gaming/audio
utilities oriented around gamegraph/db-etc
stuff related to graphs, databases, and graph databasesinterpreter-like
similar to openinterpreter, executes on a filesystemKANs
everything i could fine lolLLM actual
LLM training
tools and paperslocal
local/private/etc aiMCP
visualizations for source codemike stuff
MLX
fmr llm based toolkit, now mlx stuffmultiagent-debate
debate architecturesnvim
neovim stuffpapers-guides-text
prompting
rag/memory
resources
rust/education
strawberry
we have it at homethe guidance thing
this weeks stars
we use dis nowtraining and finetuning
transcription
video/img/diffusion
vim-zellij-dotfiles-etc
what it says on the boxStars
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Pressure-aware drawing and lesson workspace with a local Codex learning coach
A minimal, secure Python interpreter written in Rust for use by AI
A relative time formatting library, with no code.
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…
Extra heads for your pi coding agent: live oversight through prompt-cache replay
Listing of community-curated resources to find topical remote freelance & contract work for software developers, web designers, and more!
Open-source AI job search: scan job portals, evaluate listings with a structured A-F rubric into a 1.0-5.0 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Cod…
Fast and reliable Ashby job board scraper for Apify
interpretation utility for document and code ingestion as well as parsing model outputs and tool calls
Companion code for the global workspace interpretability paper
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
The visual feedback tool for agents.
Manage worktrees without managing worktrees.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Noumena's internal version of your favorite coding tui but improved and optimized for our inference stack
Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Expert-thinking AGENTS.md profiles that teach AI agents to reason like senior scientists and engineers.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
seven open source ai music models inside the DAW