Open systems / 03
Open-source releases worth evaluating.
Find new AI tools and meaningful releases with source links, adoption context, and practical tradeoffs.
anthropics/anthropic-sdk-python v1.2.0
## 1.2.0 (2026-08-27) Full Changelog: [v1.1.0...v1.2.0](https://github.com/anthropics/anthropic-sdk-python/compare/v1.1.0...v1.2.0) ### Features * **api:** beta files/skills namespaces use GA shapes; drop dated beta header pins ([9df4565](https://github.com/anthropics/anthropic-…
github.com21 days agoView details
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
github.com5 months ago51 ptsView details
langchain-ai/langchain langchain==1.3.18
Changes since langchain==1.3.17 release(langchain): 1.3.18 (#39966) fix(langchain): preserve content-block shape in PIIMiddleware redaction (#39894) fix(core): shore up indexing in genai v1 streaming content (#39964)
github.com21 days agoView details
The best-benchmarked open-source AI memory system. And it's free.
github.com5 months ago48 ptsView details
NirDiamant/Agent_Memory_Techniques
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
github.com4 months ago30 ptsView details
Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.
github.com4 months ago32 ptsView details
<details open> models : support nanbeige4.2-3B (#27730) Co-authored-by: admin <lizongqiang@kanzhun.com> </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/43308396> **macOS/iOS:** - [macOS Apple Silicon (arm64)](…
github.com22 days agoView details
<details open> hexagon: support for multi-NPU devices (IQ9, IQ10) and fully asynchronous backend (#26501) * hexagon: use non-host bufs by default and make the backend fully async * hex-hb: remove optional hostbuf support and fix async copy * hex-unary: relax supported unary chec…
github.com22 days agoView details
ather-techie/rag-interview-system
A complete collection of RAG interview questions, answers (1297 questions & 52 RAG types), system design scenarios, architecture patterns, and production-ready concepts.
github.com4 months ago22 ptsView details
## [3.5.0](https://github.com/openai/openai-python/compare/v3.4.0...v3.5.0) (2026-08-27) ### Features * **api:** make function call output call IDs optional ([#3738](https://github.com/openai/openai-python/issues/3738)) ([c74501d](https://github.com/openai/openai-python/commit/c…
github.com22 days agoView details
Editable, part-aware 3D generation from text or reference images. Open-source client for nova3d.xyz.
github.com4 months ago29 ptsView details
<details open> llama: add token ID tracking to KV cell (#27762) * kv: track token id * rm get_prev_tokens, move it to the main pr * nits * add get_prev_tokens </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/43…
github.com22 days agoView details
## [3.4.0](https://github.com/openai/openai-python/compare/v3.3.1...v3.4.0) (2026-08-25) ### Features * **api:** Add obfuscation field to ChatCompletionChunk ([#3690](https://github.com/openai/openai-python/issues/3690)) ([c7d8e1d](https://github.com/openai/openai-python/commit/…
github.com22 days agoView details
CodeAbra/iai-personal-memory-engine
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
github.com4 months ago29 ptsView details
Lightweight coding agent written in Rust, optimized for memory footprint and performance
github.com4 months ago32 ptsView details
anthropics/anthropic-sdk-python v1.1.0
## 1.1.0 (2026-08-26) Full Changelog: [v1.0.0...v1.1.0](https://github.com/anthropics/anthropic-sdk-python/compare/v1.0.0...v1.1.0) ### Features * **api:** add `updates` thinking display mode (beta) ([eb4a73f](https://github.com/anthropics/anthropic-sdk-python/commit/eb4a73fdddc…
github.com22 days agoView details
TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
github.com5 months ago44 ptsView details
huggingface/transformers v5.16.1
# Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) # GLM-5.3-Flash <img width="4239" height="2643" alt="image" src="https://github.com/user-attachments/assets/17bc9c29-758b-44c8-8230-42f945ded209" /> GLM-5.3-Flash, the first **natively multimo…
github.com22 days agoView details
huggingface/transformers v5.16.0
# Release v5.16.0 ## New Model additions ### Qwen4-Exp <img width="2241" height="693" alt="image" src="https://github.com/user-attachments/assets/c838b5ba-ffea-42da-baa9-3f66178e3671" /> Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key compone…
github.com23 days agoView details
Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
github.com5 months ago40 ptsView details
数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents
github.com5 months ago43 ptsView details
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.
github.com5 months ago42 ptsView details
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
github.com4 months ago38 ptsView details
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
github.com5 months ago41 ptsView details
<details open> ggml-meta: propagate buffer usage and call init on the new tensors (#27586) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/43044002> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://githu…
github.com23 days agoView details
"Vibe-Trading: Your Personal Trading Agent"
github.com5 months ago45 ptsView details
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
github.com4 months ago33 ptsView details
Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com
github.com4 months ago19 ptsView details
EvoLinkAI/awesome-gpt-image-2-API-and-Prompts
GPT-Image-2 API and Prompts
github.com5 months ago42 ptsView details
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
github.com4 months ago34 ptsView details
<details open> kleidiai: Rework KleidiAI Build System/Integration (#26077) * Rework KleidiAI Build System/Integration Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@arm.com> * Add fp16 guard, and fix cmake caching issue Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@ar…
github.com23 days agoView details
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
github.com5 months ago37 ptsView details
## Overview llama.cpp 0.3.0 introduces the dots3-note multimodal model (with a new DSA-ISWA KV cache), MTP support for GLM-4.5-Air, and tensor-split (`-sm tensor`) plus multi-sequence rollback fixes for DeepSeek 4. ggml is bumped to v0.22.0 (meta-backend tensor split, per-op Met…
github.com24 days agoView details
<details open> grammar : parse \- in char classes as literal hyphen (#27591) * grammar : accept "\-" escape in character classes gbnf_escape_char_class() escapes '-' as "\-" but parse_char() rejected that escape, so generated tool-call grammars failed to parse. Assisted-by: Clau…
github.com24 days agoView details
<details open> sycl : mark tq2_0 as not supported (#27660) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/42777546> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/release…
github.com24 days agoView details
Source control for agents. Use multiple coding agents, track their changes and query them in one place
github.com4 months ago37 ptsView details
Embedded retrieval library built on Parquet. Fast, efficient, and scalable.
github.com4 months ago19 ptsView details
langchain-ai/langchain langchain==1.3.17
Changes since langchain==1.3.16 release(langchain): 1.3.17 (#39893) fix(langchain): frame custom HITL rejection reasons (#39773) chore(deps): bump minor and patch dependencies (#39869)
github.com24 days agoView details
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
github.com5 months ago38 ptsView details
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
github.com5 months ago38 ptsView details
<details open> metal : per-device tuned (Q, NE) for flash-attn vec (#26570) * metal : per-device tuned (Q, NE) for flash-attn vec (#25750) * rebase Q-generic FA vec body from 01dc93607 (#23114) * add 53 f16 (Q,NE) flash-attn vec instantiations (vec 80 -> 133) * add FA vec (Q,NE)…
github.com24 days agoView details
Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Feishu, DingTalk, Telegram, WhatsApp and H5 access.
github.com5 months ago42 ptsView details
One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界.
github.com5 months ago32 ptsView details
Agentic Voice Notes for iPhone and macOS - Rust, Dioxus, LanceDB + RIG + SQLite
github.com4 months ago22 ptsView details
ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company
github.com4 months ago32 ptsView details
rohitg00/ai-engineering-from-scratch
Learn it. Build it. Ship it for others.
github.com6 months ago47 ptsView details
Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, retries, circuit breakers, key rotation, singleflight, and Python/TypeScript/Rust parity.
github.com4 months ago21 ptsView details
A vector index built on TurboQuant, written in Rust with Python bindings
github.com5 months ago42 ptsView details
Newsletter
Get practical AI engineering notes
Receive source-checked analysis of models, agents, evaluation, retrieval, and production reliability. Sent only when there is useful work to share.