DeepSeek ships V4.1-Flash: asymmetric MoE, 1/4 the KV cache
552B MoE, native vision, 8B/16B active params, MIT weights. The KV-cache compression DeepSeek wants agents to live with.
lean-ctx: local AI Value Gate with withdrawn benchmark
yvgude/lean-ctx is an Apache-2.0 Rust binary that compresses reads, proxies requests, and tracks costs across 30+ AI coding agents — but its headline benchmark is withdrawn.
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.
walgit: open-source Cursor Continuity design
walgit turns any S3 or GCS bucket into a stateless Git server — one Rust binary, MIT-licensed, an open implementation of Cursor's 'Continuity' design.
DeepSeek ships `dsh`: MIT agent harness
DeepSeek's dsh agent harness (MIT) hit ~165K GitHub stars in six days; every part — model adapter, tools, agent loop — is a replaceable Cordis plugin. Developer preview.
OpenWiki: LangChain's CLI that lets agents maintain their own docs
OpenWiki is a TypeScript CLI from LangChain that writes AGENTS.md, CLAUDE.md, and a local wiki from a repo or your personal sources — and updates them in CI.
Ratel: BM25 tool catalog cuts AI agent context spend 87%
Ratel (ratel-ai/ratel, 186★, Apache-2.0 core + MIT SDKs) ships an in-process BM25 tool catalog. On BFCL v3: ~87% fewer tokens, tool selection within ±5 points.
Mistral opens Leanstral 1.5: 6B-active Apache-2.0 Lean 4 prover
Apache-2.0 Leanstral 1.5 (119B/6B MoE) saturates miniF2F, hits 587/672 PutnamBench, sets SOTA on FATE-H and FATE-X, and finds 5 unknown bugs in 57 Rust repos — at ~$4 per problem.
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.
DeepSeek DeepSpec: open-source speculative decoding
DeepSeek published DeepSpec, a full-stack MIT-licensed codebase for training and evaluating draft models for speculative decoding, bundling DSpark, DFlash, and Eagle3.
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.
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.
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.
DiffusionGemma: 1,000+ tokens/sec open-weights text gen
Google DeepMind's June 10, 2026 release: a 26B/3.8B text-diffusion model denoising 256 tokens in parallel; ~4x faster than AR on a single H100, Apache 2.0, explicitly experimental.
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.