Trending AI Tools

Latest frameworks, libraries, and tools gaining traction on GitHub this week — filtered for AI/ML relevance.

Looking for foundational picks? Browse the Essential Repos →

Language:

53 tools

#14.6k this week
utopia5.4k
deeplethe · updated 1w ago

World's first open-source enterprise world model.

Rustagent-memorybitemporalgraphrag
View on GitHub ↗
#22.3k this week
miuuyy · updated 2w ago

Integrates ChatGPT Web (Pro) into Codex, enabling context, tools, streaming, and image support beyond Codex limits.

TypeScriptchatgptchatgpt-procodex
View on GitHub ↗
#3930 this week
XiaoDuoYa · updated 1w ago

Integrates ChatGPT for high‑level planning with Codex for code generation, enabling AI agents to plan and execute tasks.

TypeScriptai-agentschatgptcodex
View on GitHub ↗
#4820 this week
OpenBot4.4k
CopilotKit · updated 2w ago

Provides isolated AI coworker environments with pre‑planned actions, browser, files, and tool access, enabling AG‑UI agent integration.

TypeScriptag-uiagent-governanceai-agents
View on GitHub ↗
#5447 this week
VoiceMem861
xzf-thu · updated 1w ago

Provides streaming, long‑term memory for voice agents, separating factual and emotional data across left and right brain modules.

Pythonaiai-agentsai-tools
View on GitHub ↗
#6312 this week
Fuxi3.4k
fuxicodex · updated 2w ago

Fast, terminal‑based AI coding agent that edits code, runs commands, and cost‑effectively routes tasks across LLM providers.

Pythonagentaiai-agent
View on GitHub ↗
#7312 this week
HelixWorld606
NoizAI · updated 1w ago

HelixWorld creates real‑time interactive audio‑visual worlds using generative AI and spatial audio.

Pythonaudio-visualgenerative-airealtime
View on GitHub ↗
#8282 this week
kimi-k3-in-c7.2k
FareedKhan-dev · updated 1mo ago

Runs a 2.78‑trillion‑parameter Kimi K3 LLM inference on a single CPU using only 8.24 GB RAM.

Cavx2c99cpu-inference
View on GitHub ↗
#9279 this week
unlazy3.1k
Leonxlnx · updated 1w ago

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

JavaScriptai-agentsclaudeclaude-code
View on GitHub ↗
#10245 this week
syv-ai · updated 2w ago

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

Pythonkv-cachellm-inferencelocal-llm
View on GitHub ↗
#11245 this week
moli1.8k
lexmount · updated 3w ago

Rust-powered cloud browser automates AI agents via Playwright and Puppeteer.

Rustai-agentsai-toolsbrowser
View on GitHub ↗
#12214 this week
KiroCrew3.7k
kirodotdev · updated 1mo ago

A persistent workspace for development work that self-improves and continues beyond one session.

Pythonagentagentic-aiagents
View on GitHub ↗

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING