Skip to content

Open systems / 03

Open-source releases worth evaluating.

Find new AI tools and meaningful releases with source links, adoption context, and practical tradeoffs.

  1. buildingjoshbetter/TrueMemory

    The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

    github.com6 months ago26 ptsView details

  2. langchain-ai/langchain langchain-openai==1.5.0

    Changes since langchain-openai==1.4.3 release(openai): 1.5.0 (#39629) feat(openai): support openai 3.0 SDK (#39613) chore(partners): bump langgraph floor in openai and huggingface lockfiles (#39617)

    github.com1 month agoView details

  3. ggml-org/llama.cpp b10405

    <details open> ggml-hip : remove -funsafe-math-optimizations (#26696) It enables -fassociative-math, which reassociates FP reductions and can flip greedy argmax on RDNA3.5 (e.g. MTP speculative decode diverging from the non-speculative baseline). Drop it so HIP builds are IEEE-c…

    github.com1 month agoView details

  4. kunchenguid/treehouse

    Manage worktrees without managing worktrees.

    github.com6 months ago32 ptsView details

  5. ggml-org/llama.cpp b10400

    <details open> ggml : fix arm builds, unused var (#26991) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10400/llama-b10400-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64…

    github.com1 month agoView details

  6. langchain-ai/langchain langchain-anthropic==1.5.6

    Changes since langchain-anthropic==1.5.5 release(anthropic): 1.5.6 (#39622) fix(anthropic): normalize `tool_search_tool_result` blocks (#39621) fix(anthropic): correct model profile data for Fable 5, Sonnet 5, Opus 4.1 (#39604)

    github.com1 month agoView details

  7. fim-ai/fim-one

    Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

    github.com6 months ago32 ptsView details

  8. antoinezambelli/forge

    A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows

    github.com7 months ago33 ptsView details

  9. Shpigford/chops

    Your AI agent skills, finally organized. A macOS app to browse, edit, and manage skills across Claude Code, Cursor, Codex, Windsurf, and Amp.

    github.com6 months ago33 ptsView details

  10. ggml-org/llama.cpp b10375

    <details open> chat : tighten bare function parsing for Qwen models (#26793) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10375/llama-b10375-bin-macos-arm64.tar.gz) - macOS A…

    github.com1 month agoView details

  11. najmuzzaman-mohammad/gawkbot

    open source grok bot. gawk bots automate your menial work via AI models and build you microapps to manage the outcome, so that you have a false sense of control.

    github.com5 months ago32 ptsView details

  12. ggml-org/llama.cpp b10373

    <details open> imatrix.cpp: Move finite check and only check touched experts (#26861) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10373/llama-b10373-bin-macos-arm64.tar.gz)…

    github.com1 month agoView details

  13. bigint/rag.computer

    Self-hostable RAG platform - document ingestion, embedding, and vector search behind a simple REST API

    github.com5 months ago20 ptsView details

  14. ggml-org/llama.cpp b10369

    <details open> mtmd: support pocket-tts (#26871) * adapt the api * text model ok * working impl, need verify and clean up * mtmd: build the pocket-tts transposed convolutions as GEMM + col2im ggml_conv_transpose_1d has no grouped mode, so the depthwise upsample was built as one…

    github.com1 month agoView details

  15. vektori-ai/vektori

    Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.

    github.com5 months ago21 ptsView details

  16. openai/openai-python v3.0.0

    ## [3.0.0](https://github.com/openai/openai-python/compare/v2.54.0...v3.0.0) (2026-08-12) ### ⚠ BREAKING CHANGES * **api:** HTTPX2 is now the default HTTP client, and `httpx` is no longer installed automatically. Applications using custom HTTPX clients, transports, or configurat…

    github.com1 month agoView details

  17. ggml-org/llama.cpp b10362

    <details open> tests : disable backend sampler hip multi output (#26878) * test-backend-sampler: skip multi_output_sampling_chain on HIP The new multi_output_sampling_chain test uses top_k, whose backend probs path needs CUB (unavailable on HIP), so sampled_probs is null and the…

    github.com1 month agoView details

  18. vixhal-baraiya/pageindex-rag

    Vectorless, Reasoning-Based Retrieval-Augmented Generation (RAG)

    github.com5 months ago20 ptsView details

  19. langchain-ai/langchain langchain-anthropic==1.5.5

    Changes since langchain-anthropic==1.5.4 release(anthropic): 1.5.5 (#39597) fix(anthropic): report reasoning tokens in usage metadata (#39590) fix(anthropic): fix `KeyError` on rename in Claude file-tool middleware (#39293) chore(model-profiles): refresh model profile data (#392…

    github.com1 month agoView details

  20. langchain-ai/langchain langchain==1.3.15

    Changes since langchain==1.3.14 release(langchain): 1.3.15 (#39595) feat(langchain): expose `trace_policy` on `AgentMiddleware` (#38910) chore(langchain): fix type errors in tests (#39589) chore: bump h2 from 4.3.0 to 4.4.1 in /libs/langchain_v1 (#39324) fix(langchain): preserve…

    github.com1 month agoView details

  21. openai/openai-python v2.54.0

    ## [2.54.0](https://github.com/openai/openai-python/compare/v2.53.0...v2.54.0) (2026-08-11) ### Features * **api:** Add new Responses model identifiers ([#3595](https://github.com/openai/openai-python/issues/3595)) ([0652787](https://github.com/openai/openai-python/commit/065278…

    github.com1 month agoView details

  22. DeadWaveWave/opencove

    Your infinite canvas workspace for agents, tasks, knowledge, and research. An infinite canvas for Claude Code, Codex, terminals, tasks, and notes.

    github.com6 months ago32 ptsView details

  23. langchain-ai/langchain langchain-core==1.5.4

    Changes since langchain-core==1.5.3 release(core): 1.5.4 (#39592) fix(core): compat with pydantic 2.14 (#39328) fix(core): stop StructuredPrompt from mutating caller kwargs (#39174) fix(core): preserve flat tool args schema for `RootModel` runnables (#39307) fix(core): close int…

    github.com1 month agoView details

  24. ggml-org/llama.cpp b10361

    <details open> model : fix SWA not being enabled for EXAONE 4.5 (#26848) * model : fix SWA not being enabled for EXAONE 4.5 load_arch_hparams tests `hparams.n_layer() == 64` before LLM_KV_NEXTN_PREDICT_LAYERS has been read. n_layer() returns n_layer_all - n_layer_nextn and n_lay…

    github.com1 month agoView details

  25. unohee/OpenSwarm

    OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.

    github.com6 months ago29 ptsView details

  26. Stonewuu/ai-fusion-video

    【融光】 - 基于 Agent 的全流程AI短剧/漫剧/视频创作平台 - Java & agentscope2.0 | Agent-based end-to-end AI creation platform for short dramas, motion comics, and videos – built on Java & & agentscope 2.0.

    github.com6 months ago32 ptsView details

  27. vllm-project/vllm v0.27.1

    This is a patch release on top of v0.27.0. - Support quantized DSpark Markov heads (#50424)

    github.com1 month agoView details

  28. friuns2/codex-mobile

    🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀

    github.com6 months ago29 ptsView details

  29. Ambuj123-lab/agentic-rag-financial-parser

    Enterprise RAG ecosystem managing 32000+ semantic chunks. Features hybrid parsing (LlamaParse/PyMuPDF) and 256-dim MRL embeddings for 512MB RAM environments

    github.com5 months ago20 ptsView details

  30. vllm-project/vllm v0.27.0

    # vLLM v0.27.0 Release Notes ## Highlights This release features 561 commits from 242 contributors (64 new)! * **Kimi K3 support** with a full stack landing in one release: core model files and kernels (#50089, #50000), Python (#50093) and Rust (#50104) frontends, AttnRes kernel…

    github.com1 month agoView details

  31. huggingface/transformers v5.15.0

    # Release v5.15.0 ## New Model additions ### Meta Muse Glimmer Muse Glimmer, released today, is Meta’s new multimodal model, especially designed for agentic use cases. Distilled from Muse to 30B parameters, and released under the Apache 2.0 license, it can be deployed to local s…

    github.com1 month agoView details

  32. MakazhanAlpamys/Soup

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    github.com7 months ago34 ptsView details

  33. api7/aisix-archived

    An open source, Native AI Gateway and LLM proxy built in Rust

    github.com5 months ago18 ptsView details

  34. GaeaRuiW/kube-llmops

    github.com6 months ago20 ptsView details

  35. OrlojHQ/orloj

    An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.

    github.com6 months ago21 ptsView details

  36. hanlulong/awesome-ai-for-economists

    A curated list of AI tools, libraries, and resources for economics research, teaching, and policy analysis. Maintained by the OpenEcon team.

    github.com6 months ago28 ptsView details

  37. SixHq/Overture

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server that visually maps out the execution plan of any AI coding agent as an interactive flowchart/graph before the agent begins writing code.

    github.com7 months ago28 ptsView details

  38. tma1-ai/tma1

    Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.

    github.com6 months ago21 ptsView details

  39. onyx-dot-app/EnterpriseRAG-Bench

    Dataset and benchmark for RAG on company internal documents.

    github.com7 months ago27 ptsView details

  40. gracezhao1997/Awesome-Video-World-Models-with-AR-Diffusion

    A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, and Enthusiasts.

    github.com7 months ago28 ptsView details

  41. timschmidt/synaps-cad

    The AI-powered 3D CAD IDE — edit code, visualize in 3D, and reshape your designs with natural language.

    github.com6 months ago26 ptsView details

  42. ferro-labs/ai-gateway

    Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.

    github.com6 months ago24 ptsView details

  43. anthropics/anthropic-sdk-python v0.121.0

    ## 0.121.0 (2026-08-07) Full Changelog: [v0.120.2...v0.121.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.120.2...v0.121.0) ### Features * **api:** add `mid-conversation-tool-changes-2026-07-01` beta ([c7d1531](https://github.com/anthropics/anthropic-sdk-python…

    github.com1 month agoView details

  44. GenielabsOpenSource/spine-animation-ai

    AI-powered Claude skill for Spine 2D skeletal animation — auto-rig, animate, and preview characters

    github.com6 months ago26 ptsView details

  45. oracle/vecdb-python-sdk

    Python SDK for vector search, semantic search, RAG, embeddings, and AI agents on Oracle AI Database

    github.com5 months ago18 ptsView details

  46. ogham-mcp/ogham-mcp

    Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode

    github.com6 months ago21 ptsView details

  47. Keesan12/martin-loop

    Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loops, and prove ROI across every repo.

    github.com5 months ago23 ptsView details

  48. bandr-ai/vektori

    Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.

    github.com5 months ago21 ptsView details

  49. openai/openai-python v2.53.0

    ## [2.53.0](https://github.com/openai/openai-python/compare/v2.52.1...v2.53.0) (2026-08-03) ### Features * **api:** Add gpt-5.5 and tool name/namespace to Responses types ([#3569](https://github.com/openai/openai-python/issues/3569)) ([dd1202d](https://github.com/openai/openai-p…

    github.com1 month agoView details

  50. ZenSystemAI/Zengram

    A Multi Agent Memory MCP That Connect Agents Across Systems and Machines

    github.com6 months ago18 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.