This media is not supported in your browser
VIEW IN TELEGRAM
📦 runetes/maiao
Maiao
Maiao is the command-line companion that finally brings the genius of stacked pull requests to your favorite git hosting platforms. Instead of forcing your team to review one massive, terrifying pull request, this clever tool automatically breaks your local branch down into small, highly focused commits where every single commit gets its own independent pull request. It builds the entire stack with clean parent-child dependencies across GitHub, GitLab, and Bitbucket, and even automatically handles rebases and updates when you run quick fixups. It is the absolute easiest way to keep your code reviews fast, atomic, and completely painless.
📰 https://news.ycombinator.com/item?id=49441666
🆔 @hackernewsgithubprojects
Maiao
Maiao is the command-line companion that finally brings the genius of stacked pull requests to your favorite git hosting platforms. Instead of forcing your team to review one massive, terrifying pull request, this clever tool automatically breaks your local branch down into small, highly focused commits where every single commit gets its own independent pull request. It builds the entire stack with clean parent-child dependencies across GitHub, GitLab, and Bitbucket, and even automatically handles rebases and updates when you run quick fixups. It is the absolute easiest way to keep your code reviews fast, atomic, and completely painless.
📰 https://news.ycombinator.com/item?id=49441666
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 friday-platform/friday-studio
Friday Studio
Friday Studio turns your casual, natural-language chat requests into rock-solid, repeatable automation files you can run forever. While standard AI prompts drift and decay over time, this clever self-hosted platform bridges the gap by letting you design workflows in conversation, then instantly capturing them as version-controlled configurations. It bundles its own daemon, an interactive playground, and integrations for tools like email or browsers. You get real, autonomous agents that can tackle your middle-of-the-night tasks without you writing schedulers or API integrations from scratch. It is the ultimate tool for turning messy AI ideas into predictable, scheduled background jobs.
📰 https://news.ycombinator.com/item?id=47981311
🆔 @hackernewsgithubprojects
Friday Studio
Friday Studio turns your casual, natural-language chat requests into rock-solid, repeatable automation files you can run forever. While standard AI prompts drift and decay over time, this clever self-hosted platform bridges the gap by letting you design workflows in conversation, then instantly capturing them as version-controlled configurations. It bundles its own daemon, an interactive playground, and integrations for tools like email or browsers. You get real, autonomous agents that can tackle your middle-of-the-night tasks without you writing schedulers or API integrations from scratch. It is the ultimate tool for turning messy AI ideas into predictable, scheduled background jobs.
📰 https://news.ycombinator.com/item?id=47981311
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 abdoknbgit/tau
Tau
Tau is the terminal assistant that actually adapts to how you get work done. Think of it as a highly customizable AI companion built straight into your command line, complete with its own interactive interface and custom agent workflows. Instead of just spit-shining code, you can build specialized tasks, coordinate different agents, and integrate tools to handle complex steps like Git history recall or even browser automation. It bridges the gap between raw shell commands and a smart assistant, giving you native tool support and plugins right where you already work. Download it to upgrade your daily terminal workflow into an autonomous workspace.
🆔 @hackernewsgithubprojects
Tau
Tau is the terminal assistant that actually adapts to how you get work done. Think of it as a highly customizable AI companion built straight into your command line, complete with its own interactive interface and custom agent workflows. Instead of just spit-shining code, you can build specialized tasks, coordinate different agents, and integrate tools to handle complex steps like Git history recall or even browser automation. It bridges the gap between raw shell commands and a smart assistant, giving you native tool support and plugins right where you already work. Download it to upgrade your daily terminal workflow into an autonomous workspace.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 bobby-gray/open-tabletop-gm
Open Tabletop GM
Open Tabletop GM offloads all mechanical game elements like dice rolls and health tracking to a local Python toolchain so your artificial intelligence can focus purely on storytelling. This smart framework acts as a persistent virtual game master for tabletop roleplaying games and runs on almost any language model. It ships with Dungeons and Dragons fifth edition as a reference, but you can swap in any game system using simple markdown files. An optional companion app even renders live stats, animated weather-reactive skies, and sound effects on a shared display. It is the ultimate way to bring intelligent, automated storytelling to your next game night.
🆔 @hackernewsgithubprojects
Open Tabletop GM
Open Tabletop GM offloads all mechanical game elements like dice rolls and health tracking to a local Python toolchain so your artificial intelligence can focus purely on storytelling. This smart framework acts as a persistent virtual game master for tabletop roleplaying games and runs on almost any language model. It ships with Dungeons and Dragons fifth edition as a reference, but you can swap in any game system using simple markdown files. An optional companion app even renders live stats, animated weather-reactive skies, and sound effects on a shared display. It is the ultimate way to bring intelligent, automated storytelling to your next game night.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 maisem/tailmix
Tailmix
Tailmix is the multi-profile manager that finally lets you connect to several Tailscale networks at the same exact time. Normally, if you need to access both your work network and your personal setup, you are stuck constantly logging in and out because the standard client only allows one active connection. This project solves that headache by running a separate, isolated engine for each network profile behind a single, shared virtual network interface on your machine. It automatically handles IP conflicts and routes your traffic to the right network based on simple rules you set.
📰 https://news.ycombinator.com/item?id=49457539
🆔 @hackernewsgithubprojects
Tailmix
Tailmix is the multi-profile manager that finally lets you connect to several Tailscale networks at the same exact time. Normally, if you need to access both your work network and your personal setup, you are stuck constantly logging in and out because the standard client only allows one active connection. This project solves that headache by running a separate, isolated engine for each network profile behind a single, shared virtual network interface on your machine. It automatically handles IP conflicts and routes your traffic to the right network based on simple rules you set.
📰 https://news.ycombinator.com/item?id=49457539
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 dryweather-2544/fathom-starmap
Fathom Starmap
Your digital notebook is secretly a stunning, gravity-defying universe waiting to be explored. Fathom Starmap is a brilliant desktop plugin that transforms your personal vault of notes into a living, fully interactive three-dimensional galaxy where every single note becomes a glowing star. Your folders naturally cluster into colorful constellations while your links act as glowing threads of light pulling them together. It features a fully simulated black hole that literally bends the starlight behind it to swallow your archived files, and you can even press a key to fly a spaceship directly through your notes. It is a wonderfully creative way to watch your ideas drift, orbit, and expand.
🆔 @hackernewsgithubprojects
Fathom Starmap
Your digital notebook is secretly a stunning, gravity-defying universe waiting to be explored. Fathom Starmap is a brilliant desktop plugin that transforms your personal vault of notes into a living, fully interactive three-dimensional galaxy where every single note becomes a glowing star. Your folders naturally cluster into colorful constellations while your links act as glowing threads of light pulling them together. It features a fully simulated black hole that literally bends the starlight behind it to swallow your archived files, and you can even press a key to fly a spaceship directly through your notes. It is a wonderfully creative way to watch your ideas drift, orbit, and expand.
🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 qwenlm/qwen3.8-flash-next
Qwen3.8-Flash-Next
The multimodal model that previews the next generation of artificial intelligence architecture, qwen3.8-flash-next is an open-weight release built to prove that massive scale does not require massive hardware. Alibaba has opened the weights for this model to give developers a sneak peek at their upcoming architecture, featuring a hybrid design that compresses long conversations and scales model capacity using smart memory lookup tables. By activating only a fraction of its parameters at any given moment, it cuts training and inference costs to a tiny fraction of its predecessors while delivering superior coding capabilities. It is a massive step forward for running giant models efficiently on standard developer setups.
🆔 @hackernewsgithubprojects
Qwen3.8-Flash-Next
The multimodal model that previews the next generation of artificial intelligence architecture, qwen3.8-flash-next is an open-weight release built to prove that massive scale does not require massive hardware. Alibaba has opened the weights for this model to give developers a sneak peek at their upcoming architecture, featuring a hybrid design that compresses long conversations and scales model capacity using smart memory lookup tables. By activating only a fraction of its parameters at any given moment, it cuts training and inference costs to a tiny fraction of its predecessors while delivering superior coding capabilities. It is a massive step forward for running giant models efficiently on standard developer setups.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 shadcn-labs/editorcn
editorcn
You can now drop a complete Notion style block editor into your React app with a single terminal command. The project is called editorcn, and it delivers beautiful, ready to use rich text editor components that instantly adopt your existing design theme. Instead of spending days styling toolbars and wiring up complex layouts, you get a fully composable workspace complete with slash commands, drag handles, and floating bubble menus. Because it is built on top of Tiptap, you retain complete creative control over every custom extension and shortcut. It is the easiest way to give your users a premium writing experience without the setup headache.
🆔 @hackernewsgithubprojects
editorcn
You can now drop a complete Notion style block editor into your React app with a single terminal command. The project is called editorcn, and it delivers beautiful, ready to use rich text editor components that instantly adopt your existing design theme. Instead of spending days styling toolbars and wiring up complex layouts, you get a fully composable workspace complete with slash commands, drag handles, and floating bubble menus. Because it is built on top of Tiptap, you retain complete creative control over every custom extension and shortcut. It is the easiest way to give your users a premium writing experience without the setup headache.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 cloudflare/security-audit-skill
Security Audit Skill
Turn your coding agent into an autonomous security auditor by orchestrating a clever multi-phase pipeline that hunts down exploitable bugs. Instead of relying on superficial checklist scanners, this system deploys specialized parallel agents to map out application code, launch multi-angled attacks, and automatically weed out false positives. The absolute best part is the adversarial validation phase, where a completely separate agent tries to disprove each finding, ensuring it only reports vulnerabilities with a concrete, verifiable exploit scenario. It is a brilliant way to run deep, reliable code audits right from your command line without the usual manual noise.
🆔 @hackernewsgithubprojects
Security Audit Skill
Turn your coding agent into an autonomous security auditor by orchestrating a clever multi-phase pipeline that hunts down exploitable bugs. Instead of relying on superficial checklist scanners, this system deploys specialized parallel agents to map out application code, launch multi-angled attacks, and automatically weed out false positives. The absolute best part is the adversarial validation phase, where a completely separate agent tries to disprove each finding, ensuring it only reports vulnerabilities with a concrete, verifiable exploit scenario. It is a brilliant way to run deep, reliable code audits right from your command line without the usual manual noise.
🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 zironic/h3-optimizations
H3 Optimizations
H3 Optimizations is the ComfyUI extension pack that finally stops massive video models from eating all your graphics memory. If you are trying to generate high-resolution AI video, you know how easily those massive sequence lengths can trigger out-of-memory crashes. This clever tool introduces native sparse attention and smart chunking to drastically cut down VRAM usage by gigabytes, all without hurting your video quality. It even adds a specialized memory residency limiter to keep the model weights from hogging your GPU. It is essentially free speed and massive memory savings for your video generation workflows.
🆔 @hackernewsgithubprojects
H3 Optimizations
H3 Optimizations is the ComfyUI extension pack that finally stops massive video models from eating all your graphics memory. If you are trying to generate high-resolution AI video, you know how easily those massive sequence lengths can trigger out-of-memory crashes. This clever tool introduces native sparse attention and smart chunking to drastically cut down VRAM usage by gigabytes, all without hurting your video quality. It even adds a specialized memory residency limiter to keep the model weights from hogging your GPU. It is essentially free speed and massive memory savings for your video generation workflows.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 wispr-flow-linux/wispr-flow-linux
wispr-flow-linux
Run the popular Wispr Flow voice dictation application natively on your Linux desktop. While the official app only supports macOS and Windows, this clever project repackages the official Windows installer and pairs it with a custom, clean-room Rust helper. This helper fully recreates the original app's text-injection capabilities, letting you dictate voice-to-text directly into any active window on Linux. It automatically hooks into your clipboard and virtual keyboard to type out your spoken words instantly. You get fully automated build scripts that output native debian, rpm, and AppImage packages, giving you a seamless hands-free typing experience on any major Linux distribution.
📰 https://news.ycombinator.com/item?id=48436737
🆔 @hackernewsgithubprojects
wispr-flow-linux
Run the popular Wispr Flow voice dictation application natively on your Linux desktop. While the official app only supports macOS and Windows, this clever project repackages the official Windows installer and pairs it with a custom, clean-room Rust helper. This helper fully recreates the original app's text-injection capabilities, letting you dictate voice-to-text directly into any active window on Linux. It automatically hooks into your clipboard and virtual keyboard to type out your spoken words instantly. You get fully automated build scripts that output native debian, rpm, and AppImage packages, giving you a seamless hands-free typing experience on any major Linux distribution.
📰 https://news.ycombinator.com/item?id=48436737
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 sourcegraph/zoekt
Zoekt
You can search through billions of lines of source code across thousands of git repositories instantly using three character indexing. The open source project zoekt is a dedicated search engine built specifically for raw codebases rather than standard text. By breaking down your source code into tiny trigrams, it builds an index that can execute complex regular expressions and substring matches almost immediately. It easily plugs into your local command line, git repos, or remote code hosts, scoring and ranking search results based on actual code symbols. It is the perfect tool for developers who need to navigate massive, fragmented codebases without getting slowed down by slow, traditional search tools.
🆔 @hackernewsgithubprojects
Zoekt
You can search through billions of lines of source code across thousands of git repositories instantly using three character indexing. The open source project zoekt is a dedicated search engine built specifically for raw codebases rather than standard text. By breaking down your source code into tiny trigrams, it builds an index that can execute complex regular expressions and substring matches almost immediately. It easily plugs into your local command line, git repos, or remote code hosts, scoring and ranking search results based on actual code symbols. It is the perfect tool for developers who need to navigate massive, fragmented codebases without getting slowed down by slow, traditional search tools.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 gen-verse/recuris
Recuris
Boost your long-horizon AI agents by evolving their memories instead of updating their weights or rewriting their prompts. This clever framework pairs a frozen agent with a state-grounded skill memory, capturing real execution traces to pinpoint exact points of failure. Instead of modifying a massive, bloated prompt, a meta-agent target-patches only the broken memory component, which must then pass a strict, model-free validation gate to survive. It is completely training-free and model-agnostic, meaning a memory evolved on one model transfers to others seamlessly. It is a brilliant way to slash agent errors on complex, multi-step tasks.
🆔 @hackernewsgithubprojects
Recuris
Boost your long-horizon AI agents by evolving their memories instead of updating their weights or rewriting their prompts. This clever framework pairs a frozen agent with a state-grounded skill memory, capturing real execution traces to pinpoint exact points of failure. Instead of modifying a massive, bloated prompt, a meta-agent target-patches only the broken memory component, which must then pass a strict, model-free validation gate to survive. It is completely training-free and model-agnostic, meaning a memory evolved on one model transfers to others seamlessly. It is a brilliant way to slash agent errors on complex, multi-step tasks.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 zhangzjn/awesome-smart-glasses
awesome-smart-glasses
Smart glasses are evolving from simple head-mounted displays into fully proactive, first-person intelligence platforms that can map what you see and intend directly into real-world actions. The awesome-smart-glasses repository acts as a master map for this new era, compiling cutting-edge research, hardware profiles, and real-world datasets. Instead of just listing gadgets, it tracks critical foundational capabilities like spatial mapping, first-person perception, and secure personal memory across diverse industries from healthcare to robotics. It is an invaluable goldmine for anyone wanting to see how wearable AI will actually integrate into our daily lives. Check it out to see where wearable tech is heading next.
🆔 @hackernewsgithubprojects
awesome-smart-glasses
Smart glasses are evolving from simple head-mounted displays into fully proactive, first-person intelligence platforms that can map what you see and intend directly into real-world actions. The awesome-smart-glasses repository acts as a master map for this new era, compiling cutting-edge research, hardware profiles, and real-world datasets. Instead of just listing gadgets, it tracks critical foundational capabilities like spatial mapping, first-person perception, and secure personal memory across diverse industries from healthcare to robotics. It is an invaluable goldmine for anyone wanting to see how wearable AI will actually integrate into our daily lives. Check it out to see where wearable tech is heading next.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 atongwang/world-model-simulators
world-model-simulators
Artificial intelligence is trying to build entire virtual realities from scratch, but nobody knows if they actually obey the laws of physics. That is why the world model simulators repository is such a goldmine. It gathers two hundred ground-breaking papers tracking how close artificial intelligence is to becoming a true physics simulator. Instead of just generating pretty videos, it categorizes research on how artificial worlds handle real gravity, collision, and object interaction. If you want to see how robots are training in purely hallucinated environments without falling through the floor, you need to check this out.
🆔 @hackernewsgithubprojects
world-model-simulators
Artificial intelligence is trying to build entire virtual realities from scratch, but nobody knows if they actually obey the laws of physics. That is why the world model simulators repository is such a goldmine. It gathers two hundred ground-breaking papers tracking how close artificial intelligence is to becoming a true physics simulator. Instead of just generating pretty videos, it categorizes research on how artificial worlds handle real gravity, collision, and object interaction. If you want to see how robots are training in purely hallucinated environments without falling through the floor, you need to check this out.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 leaplabthu/opdvr
Improve LLM Reasoning with OPDVR
Supercharge your AI model's math and reasoning skills by aligning teacher guidance with factual correctness. Traditional model distillation transfers knowledge from a smart teacher to a student, but it relies on dense token-level feedback that is completely blind to whether the actual final answer is correct or not. This project, opdvr, fixes this with an elegant, zero-hyperparameter gate. If a student's reasoning path leads to a wrong answer, the system instantly masks out conflicting teacher guidance. It basically ensures the student only learns positive lessons from correct steps, leading to massive accuracy gains across tough math benchmarks without any extra tuning.
🆔 @hackernewsgithubprojects
Improve LLM Reasoning with OPDVR
Supercharge your AI model's math and reasoning skills by aligning teacher guidance with factual correctness. Traditional model distillation transfers knowledge from a smart teacher to a student, but it relies on dense token-level feedback that is completely blind to whether the actual final answer is correct or not. This project, opdvr, fixes this with an elegant, zero-hyperparameter gate. If a student's reasoning path leads to a wrong answer, the system instantly masks out conflicting teacher guidance. It basically ensures the student only learns positive lessons from correct steps, leading to massive accuracy gains across tough math benchmarks without any extra tuning.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 dixin-lab/cft
cft
cft is an image relighting tool that keeps your original photo details perfectly intact while completely changing the lighting. Standard AI image editors often warp face shapes, change backgrounds, or lose the original person's identity when shifting from bright sunlight to moody shadows because they treat the process as entirely new image generation. Instead of starting from scratch, this project solves the problem by modeling the transition as a smooth path that directly carries over existing features. This means the AI isolates and shifts only the light rays while locking in your underlying facial geometry, structure, and identity. You get realistic, complex lighting adjustments that look completely natural every time.
🆔 @hackernewsgithubprojects
cft
cft is an image relighting tool that keeps your original photo details perfectly intact while completely changing the lighting. Standard AI image editors often warp face shapes, change backgrounds, or lose the original person's identity when shifting from bright sunlight to moody shadows because they treat the process as entirely new image generation. Instead of starting from scratch, this project solves the problem by modeling the transition as a smooth path that directly carries over existing features. This means the AI isolates and shifts only the light rays while locking in your underlying facial geometry, structure, and identity. You get realistic, complex lighting adjustments that look completely natural every time.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 emwstudio/voxemw
voxemw
Have a voice chat on your browser with a virtual anime companion using your own cloned voice, responding in under one and a half seconds. voxemw brings a complete virtual companion pipeline to your Apple Silicon Mac, managing voice activity detection, speech-to-text, and local voice cloning while utilizing a cloud brain for low-cost conversational intelligence. The standout feature is its real-time 3D VRM avatar rendering with server-side mouth shapes perfectly synced to every spoken word, reacting dynamically with natural expressions and head movements. It is an amazing way to experience ultra-low latency, interactive digital humans running directly on your local hardware.
🆔 @hackernewsgithubprojects
voxemw
Have a voice chat on your browser with a virtual anime companion using your own cloned voice, responding in under one and a half seconds. voxemw brings a complete virtual companion pipeline to your Apple Silicon Mac, managing voice activity detection, speech-to-text, and local voice cloning while utilizing a cloud brain for low-cost conversational intelligence. The standout feature is its real-time 3D VRM avatar rendering with server-side mouth shapes perfectly synced to every spoken word, reacting dynamically with natural expressions and head movements. It is an amazing way to experience ultra-low latency, interactive digital humans running directly on your local hardware.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 zhoushen1/qurec
Qurec
An academic project called Qurec is solving the headache of ruined photos by fixing multiple types of image damage all at once. Instead of needing one tool for blur, another for noise, and a third for bad lighting, this clever system uses query-guided instructions to clean up your pictures in one go. It works by guiding the restoration process with specific queries and calibrating how the model looks at both tiny details and the bigger picture. It is a smart, unified approach to image repair that actually understands what needs fixing, making photo restoration a whole lot smarter.
🆔 @hackernewsgithubprojects
Qurec
An academic project called Qurec is solving the headache of ruined photos by fixing multiple types of image damage all at once. Instead of needing one tool for blur, another for noise, and a third for bad lighting, this clever system uses query-guided instructions to clean up your pictures in one go. It works by guiding the restoration process with specific queries and calibrating how the model looks at both tiny details and the bigger picture. It is a smart, unified approach to image repair that actually understands what needs fixing, making photo restoration a whole lot smarter.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 teorth/erdosproblems
Erdos Problems
Erdosproblems is the community database that brings order to the legendary, unsolved mathematical challenges left behind by Paul Erdos. Instead of letting these brilliant puzzles sit scattered across textbooks, mathematicians Terence Tao and Thomas Bloom are crowdsourcing a central hub to track them all. The project links each problem directly to known integer sequences on the Online Encyclopedia of Integer Sequences and even tracks whether a solution has been verified by computer proof assistants like Lean. It is a playground for anyone who loves math, letting you help calculate sequences or track down historical proofs. Check it out to see if you can solve a piece of math history.
📰 https://news.ycombinator.com/item?id=49461053
🆔 @hackernewsgithubprojects
Erdos Problems
Erdosproblems is the community database that brings order to the legendary, unsolved mathematical challenges left behind by Paul Erdos. Instead of letting these brilliant puzzles sit scattered across textbooks, mathematicians Terence Tao and Thomas Bloom are crowdsourcing a central hub to track them all. The project links each problem directly to known integer sequences on the Online Encyclopedia of Integer Sequences and even tracks whether a solution has been verified by computer proof assistants like Lean. It is a playground for anyone who loves math, letting you help calculate sequences or track down historical proofs. Check it out to see if you can solve a piece of math history.
📰 https://news.ycombinator.com/item?id=49461053
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 joseairosa/recall
Recall
Recall is the model context protocol memory server that finally solves the problem of AI session amnesia. Instead of losing your hard-earned context, setup rules, and architecture choices every time you restart a chat or hit a token limit, this tool acts as a persistent brain extension for Claude. It stores critical patterns, decisions, and preferences once, then automatically pulls them in across any future conversation. You can self-host it using Redis or Valkey to keep your data fully private, or use their simple cloud service. It is basically the ultimate way to stop repeating your project requirements to AI assistants over and over.
🆔 @hackernewsgithubprojects
Recall
Recall is the model context protocol memory server that finally solves the problem of AI session amnesia. Instead of losing your hard-earned context, setup rules, and architecture choices every time you restart a chat or hit a token limit, this tool acts as a persistent brain extension for Claude. It stores critical patterns, decisions, and preferences once, then automatically pulls them in across any future conversation. You can self-host it using Redis or Valkey to keep your data fully private, or use their simple cloud service. It is basically the ultimate way to stop repeating your project requirements to AI assistants over and over.
🆔 @hackernewsgithubprojects