EmbeddingGemma 2: on-device multimodal embeddings under Apache 2.0
Google DeepMind's 740M open-weight EmbeddingGemma 2 maps text, images, video, and audio into one shared 768-dimensional vector space for local search and RAG.
reverify: deterministic tools judge AI claims
2akouwu/reverify pairs an LLM with a deterministic verifier: model proposes, tools check bytes, only VERIFIED claims survive. Lossless rollover replaces compaction.
Alberta scanned 466M lines of government code with Claude in 20 hours
Alberta's Ministry of Technology and Innovation scanned 466M lines of government code in 20 hours with Claude Code and ~50 agents — here is the playbook other provinces can copy.
Better Models, Worse Tools: Claude tool regression
Armin Ronacher's controlled tests show Claude Opus 4.8 and Sonnet 5 produce ~20% malformed tool calls against Pi's edit tool; older models are clean.
cognee: open-source AI memory platform for agents
cognee is an Apache-2.0 open-source AI memory platform for agents: a self-hosted knowledge graph engine with a four-method API (remember, recall, forget, improve) and a Claude Code plugin.
CodeBurn: free, local-first cost tracker for 31 AI coding tools
CodeBurn (getagentseal/codeburn) reads the session files your AI coding tools already write, breaks down every token and dollar across 31 integrations, MIT, no proxy, no API key.
oh-my-pi: a terminal agent that treats the harness as the product
can1357/oh-my-pi: a Rust-based terminal AI coding agent (fork of Mario Zechner's pi-mono) with Hashline edits, an advisor model, 40+ providers, 18-hour release cadence.
codebase-memory-mcp: zero-dep code intelligence
Pure-C, single-binary MCP server that indexes a codebase into a Tree-Sitter knowledge graph in milliseconds. 13.3k stars, MIT, 5,604 tests, 11 agents. arXiv 2603.27277 reports 83% quality at 10× fewer tokens.
Headroom: open-source token compression for AI agents
Headroom v0.27.0 is an Apache-2.0 context-compression layer for AI agents: library, proxy, agent wrapper, and MCP server. Published savings reach 92% on code search and SRE debugging.
Cloudflare `wrangler deploy --temporary` for AI agents
Cloudflare shipped `wrangler deploy --temporary` on 2026-06-19: a CLI flag that provisions a temporary Cloudflare account, deploys a Worker, and prints a claim URL — 60 minutes to claim, no human in the loop.
caveman: terse-output skill, 75k stars in 11 weeks
GitHub JuliusBrussee/caveman: a TypeScript skill for 30+ agent platforms that asks the agent to drop filler. 75k stars, MIT, 65% output-token reduction.
Google Workspace CLI (gws): Rust CLI for Workspace APIs
googleworkspace/cli (gws) is a first-party Rust CLI for every Workspace API, built dynamically from the Google Discovery Service, with 95 skill directories and opt-in Model Armor sanitization.
ponytail: MIT YAGNI skill cuts AI agent code by 80–94%
Dietrich Gebert's ponytail v4.6.0 (2026-06-15): 17.9k stars, 8 releases in 4 days. MIT YAGNI skill for Claude Code, Codex, OpenCode, Cursor, Aider, Kiro. Benchmark: 80–94% less code, 47–77% lower cost.
crewAI: multi-agent orchestration framework at 53K GitHub stars
MIT repository (crewAIInc/crewAI) with 53,499 stars and 7,488 forks as of June 14, 2026. Crews+Flows architecture, 14.27M PyPI downloads in the last month, stable release 1.14.7 from June 11, 2026.
Instructor: Pydantic structured outputs for any LLM
MIT Python library (567-labs) for extracting validated Pydantic objects from any LLM. 13.2k stars, 108 releases, 15+ providers. v1.15.2 adds log redaction.
smolagents: Hugging Face's Code-First Python Agent Library
Hugging Face's open-source Python agent library where the model writes executable code instead of JSON. 27.8k stars, Apache 2.0, v1.26.0 (May 29, 2026). Remote sandboxing is mandatory.
didilili/ai-agents-from-zero: a Chinese MIT AI agent guide
MIT Chinese guide from Datawhale with 27 chapters on LangChain, LangGraph, MCP, RAG, Skills, and fine-tuning. 1.9k stars, two completed projects in May 2026. Code is Python; prose is Chinese.