9885
See what the GitHub community is most excited about today. A bot automatically fetches new repositories from https://github.com/trending and sends them to the channel. Author and maintainer: https://github.com/katursis
#rust
ai-memory helps coding agents keep working without forgetting the plan, decisions, or failed tries between sessions. It saves notes in a simple markdown wiki, so the next agent can pick up the same task with a clear handoff. This saves time, avoids repeating setup, and makes it easier to continue work across different tools or days.
https://github.com/akitaonrails/ai-memory
#python #cli #consumer_gpu #dpo #fine_tuning #gguf #huggingface #llm #llmops #local_ai #local_llm #lora #low_vram #machine_learning #ollama #peft #python #pytorch #qlora #sft #transformers
Soup is a tool that helps you fine-tune and post-train large language models with one command, using one config file and little setup. It can work on a local GPU, even a 4 GB laptop GPU for an 8B model with layer streaming, so you can train without SSH or cloud hassle. This saves time, reduces setup pain, and makes model training easier to start and manage.
https://github.com/MakazhanAlpamys/Soup
#other
This page is a guide list for using DeepSeek inside many AI tools and coding assistants, such as terminal apps, editor plugins, and desktop clients. It shows that you can set up DeepSeek in a few minutes, which helps you start coding or chatting with DeepSeek models faster and with less setup work.
https://github.com/deepseek-ai/awesome-deepseek-agent
#typescript #3d #ai_local #ai_tools #desktop_app #modly #open_source #self_hosted
Modly is a desktop app for Windows, Linux, and Apple Silicon Mac that turns a photo into a 3D model using open source AI on your own GPU. It supports extra model and process extensions, lets you run workflows, and includes a CLI for automation. This helps you make 3D meshes locally, with more privacy, faster control, and no need for cloud services.
https://github.com/lightningpixel/modly
#rust
Switchyard is a Rust proxy and library for LLM traffic that lets coding agents keep using their normal OpenAI or Anthropic API while requests are routed to different model backends and translated as needed. It can also split traffic for testing, measure latency and errors, and use custom routing rules, which helps you run or compare models more easily without changing your agent setup.
https://github.com/NVIDIA-NeMo/Switchyard
#python #ai_agent #aippt #office #powerpoint #powerpoint_generation #ppt #pptx #presentation #slide #slides
PPT Master is a free, open-source tool that turns PDFs, DOCX files, web pages, or text into a real, editable PowerPoint with native shapes, charts, tables, animations, and speaker notes. You run it locally with an AI tool, so your files stay on your machine and you avoid platform lock-in. The benefit to you is faster slide creation with a deck you can still edit in PowerPoint, instead of a flat image file.
https://github.com/hugohe3/ppt-master
#kotlin #agent #agentic_ai #agents #ai #ai_agents #aiagentframework #genai #generative_ai #java #kotlin #llms #multi_agents #multi_agents_orchestration #multi_agents_system #spring
Embabel is a Java and Kotlin framework for building AI agents on the JVM with Spring, using typed goals, actions, and conditions instead of hard-coded prompt chains. It plans and replans at runtime, which helps you build more flexible, testable, and reusable agent flows while still fitting into existing enterprise code. The benefit to you is faster AI app development with stronger type safety, easier testing, and simpler use of LLMs, tools, and domain models in one system.
https://github.com/embabel/embabel-agent
#typescript
Paperclip is an open-source tool that helps you manage many AI agents like a company, with goals, roles, budgets, approvals, and audit logs. It lets you assign work, track costs, prevent runaway spending, and watch agents run from one dashboard, which saves time and gives you better control over automated work.
https://github.com/paperclipai/paperclip
#python
Harvey LAB is an open-source benchmark that tests how well AI agents can do real legal work, not just answer legal questions. It gives each agent instructions, case documents, and a required work product, then scores the result with expert rubrics. LAB includes more than 1,200 tasks across 24 legal practice areas. This helps you compare models, check agent quality, and build better legal AI tools with a realistic standard.
https://github.com/harveyai/harvey-labs
#other
This repo gives 151 real DevOps, SRE, and cloud interview write-ups from 85 companies, with questions on Kubernetes, Docker, Terraform, AWS, Azure, GCP, CI/CD, Linux, scripting, and SRE basics. It helps you study smarter by searching for a company or role, comparing many interview styles, and spotting common topics before your interview.
https://github.com/litu54/DevOps-Interview-Guide
#clojure
Do not spend money on the SWARM token. SwarmForge is a local tmux tool that lets multiple AI agents work together in separate worktrees, with roles like coder, cleaner, architect, and QA; it helps you build software faster and with fewer conflicts. The benefit to you is organized teamwork, safer handoffs, and a choice of small, medium, or full workflows for different project sizes.
https://github.com/unclebob/swarm-forge
#python #agent_memory #ai #ai_governance #ai_infrastructure #artificial_intelligence #context_engineering #context_graphs #data_engineering #decision_intelligence #developer_tools #explainable_ai #generative_ai #graph_rag #knowledge_graph #llm #ontology #provenance #python #reasoning #semantic_search
Semantica is an open-source tool that turns messy data into clear, connected knowledge graphs for AI. It helps you track where facts came from, explain AI decisions, find conflicts, and keep systems auditable and trustworthy. This benefits you by making AI easier to trust, easier to check, and safer to use in important work like finance, healthcare, legal, and government.
https://github.com/semantica-agi/semantica
#typescript
Cloudflare Computer is a preview tool that gives you a file system plus a place to run code, with the main state kept safely in SQLite inside a Durable Object.[Text] You can use it with a container, a shell worker, or a JavaScript worker, and each option lets you work with files and run tasks in a different way.[Text] The benefit is easier building and testing of apps, agents, and prototypes with one shared workspace, but it is not ready for production yet.[Text]
https://github.com/cloudflare/computer
#shell #graphics #infra #postgres #service #toolbox #yours
Pigsty helps you set up and run PostgreSQL fast, with high availability, backup, monitoring, and many extensions on Linux or Docker. It supports small to large setups, so you can save time, reduce mistakes, and manage a reliable database system with one command.
https://github.com/pgsty/pigsty
#rust #markdown #nodejs #ocr_routing #pdf #pdf_classification #pdf_extraction #pdf_parser #python #rust #text_extraction
pdf-inspector is a fast Rust tool that checks whether a PDF has real text or is scanned, then extracts text and turns it into clean Markdown without OCR for text PDFs. It works in Python, Node.js, Rust, and browsers, and it is useful because it can save time and cost by skipping OCR, while still giving you searchable, copyable, well-structured output for reports, papers, invoices, and legal files.
https://github.com/firecrawl/pdf-inspector
#dart #android #exif #flutter #gallery #geotiff #gpx #metadata #metadata_explorer #motion_photos #mpf #slow_motion #svg #tiff #topojson #xmp
Aves is an Android gallery app that also shows photo details and metadata. It helps you browse, search, and map media files like JPEGs, MP4s, TIFFs, SVGs, panoramas, 360° videos, and more, so you can find and understand your pictures and videos faster.
https://github.com/deckerst/aves
#typescript #effect #framework #nodejs #plugin
Meta-Framework of Spatiotemporal Composability
https://github.com/cordiverse/cordis
#typescript #agent #agent_harness #agent_os #agentic #ai #ai_agent #ai_agents #artificial_intelligence #claude_code #codex #electron #holaboss #holaos #llm #mcp #memory #model_context_protocol #runtime #typescript #workspace
holaOS is a local-first desktop workspace that lets you run agents like Claude Code, Codex, or its built-in agent together with your tools, files, apps, and shared memory. It supports macOS, Windows, and Linux, includes built-in models or your own keys, and can help you get work done with real browser control, app automation, and ready-made files. This can save you time because one setup works across agents, keeps your context, and lets you produce useful results without switching systems.
https://github.com/holaboss-ai/holaOS
#swift #ai #dictation #ios #llama_cpp #macos #swift
FluidVoice is a free, open source macOS app that turns speech into text and can also control your Mac by voice. It works mostly on your Mac, so your voice and text stay private unless you choose cloud AI, and it supports fast dictation, live text preview, and optional smart formatting.
https://github.com/altic-dev/FluidVoice
#python #cactus #gemini #gemma #llm #on_device_ai
Needle 2 is a very small tool-calling AI model that can run on low memory, work offline, and return structured results like JSON instead of free text. It helps you build apps that call tools, extract data, and fine-tune models more safely and easily, even on devices with limited RAM.
https://github.com/cactus-compute/needle
#rust #agent #ai #ai_agents #all_in_one #crm #crm_system #email #linear #mcp #messaging #notes #notion #office #rust #slack #slack_alternative #startup #startup_tools #typescript #workspace
Macro is an all-in-one workspace for teams that combines email, chat, docs, tasks, CRM, calls, and agents in one fast place, with shared team memory and links between everything. The benefit for you is less app-switching, faster teamwork, and easier finding of the right message, file, or task when you need it.
https://github.com/macro-inc/macro
#html
This tool helps you make clean, branded diagrams fast, with 27 diagram types and no need for Figma or design guesswork. It can read your website, copy your colors and fonts, and turn them into diagrams in about 60 seconds, so you save time and get visuals that match your brand.
https://github.com/cathrynlavery/diagram-design
#c_lang
Dopamine is a semi-untethered jailbreak for iOS 15 to 26(.0.1)
https://github.com/opa334/Dopamine
#python #ai #ast #claude_code #code_analysis #code_understanding #codebase_search #developer_tools #graph_database #knowledge_graph #llm #mcp #mcp_server #memgraph #monorepo #multi_language #python #rag #retrieval_augmented_generation #semantic_search #tree_sitter
Code-Graph-RAG is an open-source tool that reads a codebase, builds a graph of functions, classes, modules, and links, and lets you ask questions, find code, edit safely, and improve code in plain English. It supports many languages and can run as an MCP server for direct use with AI tools. Benefit: you can understand and change large mixed-language projects faster, with less manual searching and fewer mistakes.
https://github.com/vitali87/code-graph-rag
#typescript
Prime Agent is an open-source coding and research tool for long jobs. It uses a persistent Python workspace, built-in subagents, and saved memory so work can keep going across breaks. You can install it on macOS or Linux, start it in a project folder, and use it to run commands, edit files, and keep goals active. This helps you save time, keep progress, and handle bigger tasks with less manual work.
https://github.com/PrimeIntellect-ai/prime-agent
#other #cti #cyberthreatintelligence #osint #osint_tools_list #socmint
This is a free OSINT collection with tools and resources for many research areas like people search, flight tracking, domains, phishing, malware, images, video, business, legal records, and mapping. It helps you find the right tool faster for investigation work, and the CC0 license means you can use, change, and share it freely.
https://github.com/K2SOsint/Legendary_OSINT
#rust
celld is an open-source tool that lets you run Cloudflare Workers and Durable Objects on your own machines, with each object stored as its own SQLite database and synced through your S3-compatible bucket.[Text] This gives you easy scaling, less database contention, and smaller failure impact, while idle objects use almost no resources, which can help you save money and improve reliability.[Text]
https://github.com/denoland/celld
#python #agent_control_plane #agent_ops #ai_agents #codex #long_running_agents #loop_engineering #loopx #workflow_automation
LoopX is a local control plane for long-running AI agent work. It keeps goals, tasks, evidence, quota, and handoffs in one place so work stays clear, restartable, and easier to pass between agents and people; the benefit is less lost context, safer progress, and easier review across long projects.
https://github.com/huangruiteng/loopx
#python #agent_security #ai_agents #ai_security #benchmark #claude #claude_code #codex #cursor #llm_security #mcp #model_context_protocol #prompt_injection #threat_detection
ADR is an enterprise security system for AI agents that watches what agents do, tests them for attacks, detects risky behavior, and is being used in production at Uber; its paper was accepted to MLSys 2026. The benefit to you is better protection for AI tools like Cursor, Claude Code, and Codex, plus a way to find unsafe actions before they cause harm.
https://github.com/uber/ADR
#c_lang
DwarfStar is a fast, narrow AI engine built mainly for DeepSeek V4 Flash, with support for GLM 5.2 and, on very large-memory machines, DeepSeek V4 PRO. It runs on Mac Metal, NVIDIA CUDA, and ROCm, and can use SSD streaming or distributed setups when models do not fully fit in RAM. The benefit is that you can run powerful local models on your own hardware, use them for chat, coding, or server workloads, and keep control of speed, memory, and cost.
https://github.com/antirez/ds4