Open Source
MIT-licensed open-source AI automation with 700+ integrations and the largest open-source MCP toolkit for AI agents.
Early autonomous-agent experiment — repo archived January 2026, no longer maintained
TypeScript agent framework where agents write their own tools
Alibaba's open agent framework built for transparency, not black boxes
Open-source Indic NLP suite from IIT Madras — translating, transcribing, and understanding all 22 scheduled Indian languages.
Terminal-based AI pair programmer (open source)
All-in-one AppSec platform: SAST, SCA, IaC, secrets, DAST, and runtime protection — zero CI config required.
Stanford's instruction-tuned Llama model — trained on 52k GPT-generated instructions for $600.
Self-hosted RAG chat over your files, 60k+ GitHub stars
Open-source, local-first, end-to-end encrypted workspace
Open-source LLM evaluation and observability
Microsoft's open-source multi-agent framework
The open-source autonomous AI agent that completes multi-step tasks independently using tools and memory.
Nigeria's open multilingual LLM, capped at 1,000 users free
The viral 2023 agent loop, reborn as a self-building framework
Typed LLM functions compiled to native code, not a prompt wrapper.
Stability AI's 2023 Llama fine-tunes — non-commercial, abandoned
Government-funded sovereign AI models for 22 Indian languages
Open-source Go LLM gateway claiming microsecond overhead at scale
The first multilingual open-access large language model, created collaboratively by 1,000+ researchers.
AI agent platform for customer support, priced by conversation.
AI SQL copilot that turns plain-language questions into dialect-accurate queries across 30+ databases — from MySQL to Snowflake.
Python-first embedded vector DB, now a metered Chroma Cloud
Open-source autonomous coding agent for VS Code
Ant Group's AI coding assistant
Zhipu AI's free Copilot alternative, big in China's dev scene
Meta's 2023 open-weight code models, now archived but still usable.
Hugging Face's open-source code generation model — fully documented training for learning from scratch.
Open-source AI pull-request reviewer from Qodo
Open-source AI coding assistant — discontinued, acquired by Cursor
Open-source React/Angular UI layer for in-app AI agents
Charm's open-source, cross-platform terminal AI coding agent
Sub-100ms sandboxes for AI agents that write and run code
Pytest-style unit testing for LLM outputs, 50+ metrics, Apache 2.0
Open-model inference from $0.02 per million tokens.
China's frontier open-weight LLM lab — now shipping the V4 family at a fraction of rivals' cost
Miasma: How a Hijacked CI Pipeline Shipped Malicious npm Packages With Valid Provenance
The Miasma supply-chain attack didn't typosquat or steal an npm token — it hijacked a maintainer's CI pipeline...
KE
8 Jun
GitLab 19.0 drops Redis for Valkey by default and brings Gitaly to Kubernetes
GitLab's biggest release in a year makes Valkey the default in-memory store, removing bundled Redis from its L...
KE
1 Jun
Lablup open-sources MLXcel, an Apple-Silicon inference engine, under Apache 2.0
Lablup has released MLXcel, an open-source engine for running AI models on Apple Silicon, under the permissive...
KE
1 Jun
Three supply-chain incidents this week: Megalodon, Robinsons, and the Laravel-Lang Composer compromise
Megalodon pushed 5,718 malicious commits into 5,561 GitHub repos in six hours. The Payload ransomware group li...
JE
25 May
Llama 4 Scout and Maverick Close the Gap on Frontier Models — With a 10-Million-Token Context Window
Meta's Llama 4 Scout ships a 10-million-token context window — 10× anything in the open-source field. Maverick...
AI
10 May
China's Open-Source AI Sprint: Four Labs Drop Frontier Coding Models in 12 Days, Closing Gap With Western AI
Four Chinese AI labs — Z.ai, MiniMax, Moonshot, and DeepSeek — released open-weights coding models within 12 d...
AI
8 May
Cohere and Aleph Alpha Merge to Build Europe's "Sovereign AI" Champion — But Can It Really Challenge the US-China Duopoly?
Cohere and Aleph Alpha have merged with backing from the Canadian and German governments to create a "sovereig...
AI
8 May