- Jamshedpur, India
-
20:26
(UTC +05:30) - https://ankeshbharti.com/
- @feynon_
- @ankeshbharti.com
- https://tiles.run
- All languages
- APL
- AppleScript
- Assembly
- Astro
- Ballerina
- Batchfile
- Bikeshed
- C
- C#
- C++
- CMake
- CSS
- CWeb
- Cap'n Proto
- Clojure
- CoffeeScript
- Common Lisp
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- Elm
- Emacs Lisp
- Erlang
- F#
- Fluent
- Futhark
- GDScript
- Go
- Go Template
- Groovy
- HCL
- HTML
- Hack
- Handlebars
- Haskell
- Haxe
- JSON
- Java
- JavaScript
- Jinja
- Jsonnet
- Jupyter Notebook
- Just
- Kotlin
- LLVM
- Less
- Lua
- MDX
- MLIR
- Makefile
- Markdown
- Mathematica
- Mojo
- Motoko
- Mustache
- NCL
- Nix
- Nunjucks
- OCaml
- Objective-C
- Objective-C++
- Odin
- Open Policy Agent
- PHP
- Perl
- PowerShell
- Python
- Racket
- ReScript
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Scheme
- Shell
- Solidity
- Standard ML
- Starlark
- Stylus
- Svelte
- Swift
- TeX
- Twig
- TypeScript
- Vala
- Vim Script
- Vue
- WGSL
- WebAssembly
- YAML
- Zig
- hoon
- templ
Starred repositories
Open-source template for a durable personal AI agent — web chat, Slack, Linear, and long-term memory with user-approved saves. Eve, Nuxt, Better Auth, Vercel Connect.
Zero-config, fast `io_uring`-based HTTPS server.
HyprStream: agentic infrastructure for continous online-learning applications
a projected filesystem that turns APIs, services, and data sources into local files and directories
The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
officialcjunior / sarvam-codex
Forked from openai/codexLightweight coding agent that runs in your terminal with Sarvam AI's models 🇮🇳. Forked from OpenAI's Codex
Exa MCP for web search and web crawling!
Really simple user Controlled Authorization Networks
slime is an LLM post-training framework for RL Scaling.
A lexicon-driven AppView for ATProto.
Connect your agents with anything. Make your tools composable. Secrets stay out of agent context.
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
bluesky-social / jetstream
Forked from jazware/jetstreamA simplified JSON event stream for AT Proto
Fully open-source, end-to-end encrypted, peer-to-peer application suite.
AtomicBot-ai / Atomic-Chat
Forked from janhq/janLocal AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer.
A list of specialized clouds that span traditional infra, AI, data, connectivity, and more.
A desktop app for safely exposing local services on the Internet via Iroh tunnels using QUIC. Built in rust.
An open network cloud that you can run anywhere, backed by open source.
a fast, modern browser for the npm registry
Runtime TypeScript and ESM support for Node.js