pi-warden
Guardrails for Pi built on pi-typesafe — "steer the agent instead of interrupting you: Jev judges." Part of a small Pi-safety ecosystem from the same author as the next entry.
github.com/DevMortimer/pi-warden ↗Every genuinely useful link shared in the channel — AI tools, dev tools, websites, articles and repos — curated week by week, newest first. Collected read-only; each entry carries a two-sentence brief and its sharer.
Every kept resource, newest week first. Search and the sidebar filters narrow it down.
Guardrails for Pi built on pi-typesafe — "steer the agent instead of interrupting you: Jev judges." Part of a small Pi-safety ecosystem from the same author as the next entry.
github.com/DevMortimer/pi-warden ↗TypeSafe decisions for Pi — a batched evaluation tool, terminal playground and typed API for extensions. The foundation pi-warden builds on.
github.com/DevMortimer/pi-typesafe ↗Jasper Dekoninck releasing new versions of the BrokenArXiv and ArXivMath benchmarks.
x.com/j_dekoninck/status/2100180792601420138/photo/1 ↗QuiverAI's Arrow 2 — their latest models for generating precise, editable vector graphics.
x.com/QuiverAI/status/2100295136261349802 ↗MiniCPM5 2B PCD weights on Hugging Face — the same model family as the 16 Sept in-browser Pi announcement. The model behind that WebGPU coding-agent demo.
huggingface.co/monotykamary/MiniCPM5-2B-PCD ↗An inference provider that lets Pi (a terminal agent harness) run on Claude Code Pro/Max subscriptions instead of API keys.
github.com/pi-pod/pi-claude-agent-sdk ↗Lets you route Pi's model calls through a Claude subscription ("allow sub usage in pi"). Same cost-saving idea as pi-claude-agent-sdk: agentic coding without per-token API billing.
github.com/elidickinson/pi-claude-bridge ↗Cross-vendor 3D Gaussian Splatting trainer — video to splat to mesh, running on Vulkan or CUDA. Notable for not being CUDA-locked.
github.com/harry7557558/spirula-studio ↗A dedicated browser for responsive web development — preview a site at multiple screen sizes side by side. Built for faster, more precise responsive work.
responsively.app ↗A Rege Lab page with six little Grokbot character expressions to play with, plus downloadable editable CoAnimato files. A creative asset resource for bot and character design.
rege-dev.xyz/lab/grokbot-characters ↗Official Claude guide to prompting Opus 5.5, steering long agent runs, and checking results in Claude apps and Claude Code. A practical reference for anyone driving long agent sessions.
claude.dev/blog/getting-the-most-out-of-opus-5-5 ↗A minimal bot-icon studio — browse bot icon examples and copy a prompt to generate an icon of your own. Quick asset generation for bot projects.
grokbot-icon-studio.serio-ai.chatgpt.site/en ↗Cloudflare Quick Tunnels — free encrypted tunnels that expose localhost as a public URL. Cata plans to use it instead of the VS Code tunnel.
try.cloudflare.com ↗Symbolic regression implemented in Bend. A research-flavoured repo for anyone exploring the Bend language.
github.com/k3ybladewielder/BendSR ↗A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings. A drop-in skill for agentic security reviews.
github.com/cloudflare/security-audit-skill ↗Cloudflare engineering deep-dive on saving 100TB of RAM with math (and Rust). A solid systems-engineering read.
blog.cloudflare.com/saving-100-tb-of-ram-with-math ↗Bend 2 — a fast programming language that blocks AI mistakes via proof checking. Install with curl from bend-lang.com.
github.com/bendlang/bend ↗Announcement of a free agent search/fetch API — "killed Exa, Tavily and Brave", $0 with no quotas, from Tiny_Fish and MonidHQ.
x.com/MonidHQ/status/2100705843453079718 ↗Shared by thelaggingway with just "Another one" — context is thin, but it landed in the search-tool thread. Worth a look if you're tracking search APIs.
github.com/superagents-lab/jev-search ↗Microsoft's ArgusAgent — a persistent, reviewed multi-agent runtime for long-horizon research and engineering. Directly relevant to anyone running agents on long tasks.
github.com/microsoft/ArgusAgent ↗A markdown viewer "for vibe coders" — a simple, beautiful app for reading the .md files your AI writes: specs, plans, skills, agents and more. Pairs naturally with agent-heavy workflows.
prettymd.app ↗LiquidAI's LFM2.5 2.6B model tuned for RLCD, shared in the context of Jev's API and concepts. A small local model for anyone experimenting with RLCD-style agent loops.
huggingface.co/monotykamary/LFM2.5-2.6B-RLCD ↗A 1B RLCD-tuned Qwen 2.5 that kenn tried locally "to get a feel of how Jev's API and concepts might feel like" — and found it did fine in a roguelike spike. Useful as a tiny testbed model before spending on bigger runs.
huggingface.co/harshatheg/Qwen-2.5-1B-RLCD ↗Announcement of a coding agent (Pi) running entirely in the browser on a 2B model via WebGPU — MiniCPM5-2B + Pi with Transformers.js and 4-bit ONNX weights.
x.com/victormustar/status/2099794150879121471 ↗An experimental Rust time-series database with DuckDB SQL and tiered Parquet storage — "time settles into layers." Early-stage but interesting for anyone into time-series storage design.
github.com/monotykamary/varve ↗Ever Gauzy — an open business management platform covering ERP, CRM, HRM, ATS and project management (gauzy.co). A full open-source suite if you ever need to stand up business tooling.
github.com/ever-co/ever-gauzy ↗Demo of a universal syntax highlighter built on the new OpaqueRange web API (Chrome 152+, 2026) — syntax-highlighting different program fragments efficiently. Worth a look for anyone building code-rendering UI.
x.com/sebastienlorber/status/2099883816718323949 ↗Jakub Krehel's essay on the invisible side of design engineering — the craft that doesn't show up in the final pixels. A thoughtful read for design-minded engineers.
jakub.kr/writing/the-invisible-side-of-design-engin… ↗A reference layer for AI coding agents — real production websites with desktop and mobile captures, "real websites worth studying." Useful as grounding material when agents need to see how good sites are actually built.
inspomcp.dev ↗A small library of playful, physics-driven React elements — including a ceiling pull-cord with real Verlet rope physics. For interfaces that should feel alive rather than flat.
feralui.dev ↗A harness claiming five Qwen3.8-27B models match Claude Fable 5 on LiveCodeBench Hard — "Fable 5 level coding." The performance claims are the poster's and unverified; scarywood75 noted the implementation is Python.
github.com/slee-persis/GVS5H ↗A collection of the most essential transitions for web apps, plus a skill for agents and a Refine tool. Drop-in motion craft for web projects and the agents building them.
github.com/Jakubantalik/transitions.dev ↗A collection of design-engineering skills covering accessibility, motion and frontend craft. Pairs well with the transitions.dev repo above for leveling up UI output.
ui-skills.com ↗Oskar's announcement of "e2e", a new agent-oriented testing framework — he ported React Native Pager View's test suite from Maestro to it.
x.com/o_kwasniewski/status/2098804833880817728 ↗A collection of beautifully designed, accessible and customizable PDF components built on Takumi. Handy if you ever need to render polished PDFs from a web stack.
pdfcn.dev ↗An open-source 3D architectural editor with a local CLI, MCP tools and practical workflows for humans and agents. Niche but complete — 3D editing with agent integration baked in.
github.com/pascalorg/editor ↗A professional vector design tool "where you and your AI agents work directly on the canvas." Agent-native design tooling is still rare, which makes this one notable.
brilliant.design ↗Compares the real cost of AI — subscription allowances, model benchmarks and the price–performance frontier, with transparent sources. Useful before committing spend to any provider.
real-api-pricing.vercel.app ↗A pi extension giving the agent exactly one tool — doing file read/edit work in arm64 assembly — to stop Astra shelling out to python3, ruby and perl for file ops. Announcement; the actual link was promised in a follow-up tweet.
x.com/aliceisplaying/status/2097387613086683232 ↗Announcement of Minara Harness — pitched as "general financial intelligence for everyone", turning ideas into signals into execution, plus coding tasks like any other agent.
x.com/minara/status/2097413018510618899 ↗Daniel's post that a new herdrdev update is out with fleet management live. A product-update announcement; the herdr blog below has the substance.
x.com/imnotchalk/status/2097056509025018029/photo/1 ↗A step-by-step guide to making photorealistic 3D worlds and games — reference photos, Blender assets, sub-agents, blind critics, Three.js vs Unreal Engine, and a starter prompt. The "GPT-6 Astra" framing is the site's own marketing.
somethingbig.ai/3d-worlds ↗An open-source Palantir alternative — track 10K+ aircraft, 2K satellites and worldwide CCTV on a 3D globe, and run Nmap, DNS, WHOIS and threat-intel scans from the browser across 20+ live feeds. Free.
osirisai.live ↗An AI-native design editor pitched as an open-source Figma alternative. Worth watching if design tooling is on your radar.
github.com/open-pencil/open-pencil ↗The Herdr blog on 0.9, which brings local and remote machines into one TUI client, with Herdr Cloud coming next. Herdr's pitch: run agents anywhere, leave them running.
herdr.dev/blog/connecting-the-machines ↗An agent-harness performance optimization system — skills, instincts, memory, security and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. Directly relevant if you're tuning agent setups.
github.com/affaan-m/ECC ↗Matt Dancho's post on Microsoft's MarkItDown — turns almost any file (PDFs, Word, PowerPoint, Excel, images) into clean Markdown; claimed 100,000+ GitHub stars.
x.com/mdancho84/status/2096623235576053935 ↗Google's Magika — detects the real content of any file even when disguised (malware posing as PDF, scripts hidden as images); free and open-source.
x.com/_guillecasaus/status/2096913125266079843 ↗Tencent's "Make Every Team AI Native" CLI. The description is thin, but a Tencent-backed team-AI CLI is worth a look.
github.com/Tencent/teamai-cli ↗Cata's first pi extension — an ASCII showcase/mockup gallery of UIs for fast iteration. The shared link pointed at the commits page; normalized to the repo root.
github.com/1y33/pi-mockdeck ↗Git-native persistent memory for AI coding agents — implements Google OKF v0.2 with sub-300µs in-memory BM25 search and an embedded MCP server.
github.com/okf-memory/okf-agent-memory ↗Microsoft's tgrep — grep for large codebases with client/server support, claimed 7–50x faster than ripgrep and ugrep.
x.com/jedisct1/status/2096919996412666296 ↗"BEAM on device" — write mobile apps in Elixir with the whole BEAM running on the device, rendering native iOS and Android UI; your coding agent attaches to the running app with real state and hot-pushed fixes. Ambitious and unusual.
mobframework.com ↗"The ripgrep of AI context" — a zero-dependency C++23 CLI plus MCP server that gives coding agents a ranked, deterministic map of any repo: blast radius, tests-to-run and quality deltas. From Red Hat's emerging-tech group.
github.com/redhat-et/ripwire ↗OpenAI's developer blog on using Astra to design a house, refine everyday details, and explore it through Blender camera tours and an Unreal Engine 5 walkthrough. A concrete agentic-design case study.
developers.openai.com/blog/architectural-visualizat… ↗SponsorBar — puts a small ad in your menu bar and shares the revenue with you ("make money from your menu bar for doing nothing"), with a 10%-extra launch promo. A real launched product, though a niche one.
x.com/henry_kutrieb/status/2095901727425786300 ↗Browse Factory-generated wikis for popular open-source repositories — a preview of what living documentation looks like on real codebases before running it on your own. Nice for evaluating doc-generation tooling.
factory.com/open-source-wikis ↗A GUI for your coding agents. Description is minimal, but a visual front-end for agent harnesses is a gap worth filling.
github.com/hardbeat920/monocode ↗A search MCP server from baanish, who vouched for PR #4 personally. The shared link was the PR; normalized to the repo root.
github.com/baanish/synthetic-search-mcp ↗Nielsen Norman Group's study guide on the psychology behind UX. A solid reference for grounding design decisions in research rather than taste.
nngroup.com/articles/psychology-study-guide ↗Copy-paste animated React components from beUI. Drop-in motion without building animation primitives from scratch.
beui.dev/components/motion ↗A creative component library for Canvas, WebGL and WebGPU. For interfaces that need GPU-level visuals rather than DOM elements.
canvasui.dev ↗A tool catalog for agents — 2,630 endpoints across 47 providers (SEO, social, enrichment, ads data) callable with one key, priced per call, plus support for your own keys and skills. Tom's 2 Sep share carried his referral param; normalized to the root domain.
treg.to ↗Jason Zhou's announcement of "Claude for people-search" at a claimed $0.0089/lead versus $600 subscriptions.
x.com/jasonzhou1993/status/2094740336895840605 ↗Paper — "design, share, ship." A design tool baanish was scouting; no verdict from the channel yet. (Rykuuun's pricing-page share from 8 Sep was dropped as context-free.)
paper.design ↗Kenn wanted to fork Paseo for internal use cases but held off because it was AGPL — PR #3944 has now relicensed it to Apache. The shared link was the PR; normalized to the repo root. The license change is the news: it's forkable now.
github.com/getpaseo/paseo ↗asx8678's own repo, built after burning through tokens fast. Context is thin, but it reads as a token-efficiency tool from someone feeling the pain directly.
github.com/asx8678/elxr ↗The Elixir Forum announcing DSH, the DeepSeek Harness.
x.com/elixirforum/status/2094106034298044867 ↗Fresh — "The Terminal IDE." A terminal-based IDE worth a look if you live in the shell.
getfresh.dev ↗Monospace charts and tables for MDX and React. Handy for rendering data visuals that stay crisp in markdown contexts.
mdx-graphs.kshv.me ↗Eclipse Theia — a cloud and desktop IDE framework implemented in TypeScript. The open foundation behind several well-known IDE products.
github.com/eclipse-theia/theia ↗Open-source alternative to Jira, Linear, Monday and ClickUp. A self-hostable project-management option for teams avoiding SaaS lock-in.
github.com/makeplane/plane ↗Tencent's Hy4 preview weights in FP8 on Hugging Face — 770B total, 49B active, 1M context, open weights. For anyone with the hardware to run a frontier-scale open model.
huggingface.co/tencent/Hy4-preview-FP8 ↗A GLM-5.3-Flash quant on Hugging Face. Context is thin — thelaggingway's whole review was "Huh" — but it's another fast-model option to know about.
huggingface.co/incoai/GLM-5.3-Flash-DFlash2 ↗DBX — a 20 MB tool for managing 90+ databases. Remarkably small footprint for a universal database client.
dbxio.com/en ↗Arize AI's open-source observability platform for LLM apps — tracing, evaluation, and experimentation for agent and RAG workloads. A standard choice for watching what production agents actually do.
github.com/Arize-ai/phoenix ↗Prime Intellect's framework for training AI agents with reinforcement learning.
github.com/PrimeIntellect-ai/prime-agent ↗A Windows automation harness from the browser-use team (the web-agent library folks).
github.com/browser-use/windows-harness ↗A write-up of Spec-PTC, a speculative parallel test-time compute framework for long-horizon agents. Interesting if you follow inference-scaling tricks for agentic workloads.
alexzhang13.github.io/blog/2026/spec-ptc ↗An open-source agent microharness with persistent agency and recursive LLMs — "of bash, by bash". Minimal by design; good for experimenting with agent loops without a heavy framework.
github.com/laude-institute/headlong ↗Maxime Heckel's deep dive into shading-based motion design techniques. One of the better-written front-end animation articles; useful if you care about motion craft.
blog.maximeheckel.com/posts/shading-motion ↗An AI-native browser aimed at research workflows.
radiusbrowser.com ↗An MCP (Model Context Protocol) gateway that advertises an accuracy guarantee — unusual positioning in the MCP tooling space.
darkbloom.dev ↗Deep link into the pi coding agent's v2 harness documentation. Worth reading if you use pi or are designing your own agent harness.
github.com/earendil-works/pi/blob/harness-v2/j4/pac… ↗A browsable library of Three.js components and interactive shaders. Handy for dropping 3D effects into web projects without writing raw WebGL.
threeui.com/browse ↗Opinionated Oxlint rules that reject low-evidence TypeScript/JavaScript patterns — basically a linter config against AI-slop code. Fun and practical for teams drowning in generated code.
github.com/dmmulroy/anti-slop ↗Salesforce's announcement of Slack Code, bringing coding-agent workflows into Slack. Announcement-level; the "oh no" from the sharer suggests healthy skepticism.
salesforce.com/introducing-slack-code ↗A small repo that translates "Claudish" — AI-assistant jargon — into plain English. Niche but amusing; useful if you've ever stared at a model hedging for three paragraphs.
github.com/gvzdv/claudish-to-english ↗Micro-interactions for React, "built for the half-second after a click". A focused little library for the small animations that make UIs feel alive.
interior.dev ↗A durable agent framework pitched as "Next.js for agents" — build agents with one folder, with durability baked in.
eve.dev ↗Turns your Mac activity into a private timeline for you and your AI — local activity history as agent context.
openhistory.sh ↗A self-described "weird, playful" desktop app for building with AI agents — "less chatting, more building".
berd.xyz ↗Vercel's announcement of fx, "a tiny, open, native coding agent" from Vercel Labs, originally an internal tool.
x.com/vercel_dev/status/2089828083415355806 ↗A collection of "skills" for designers and engineers from Emil Kowalski (of Vercel/animations fame). Likely agent-skill style playbooks; worth browsing.
github.com/emilkowalski/skills ↗A tiny interactive explainer of how your phone finds itself — satellites, signal timing, and trilateration. The good kind of technical storytelling.
gps-01.dmytro.fyi ↗A library of animated React components. Another solid option in the crowded React-animation space; compare with the other UI libraries already in the archive.
rareui.com ↗Cua's announcement of the first open-source "Computer History", in early preview. Announcement-only; interesting for computer-use agent research.
x.com/trycua/status/2089770780053643397 ↗Strips multi-vendor AI provenance marks — Unicode text hygiene, statistical rewrite hooks, and C2PA handling. Legitimate hygiene tooling; obviously dual-use.
github.com/guillaumemeyer/watermarks-remover ↗"Crafted primitives for AI-native interfaces" — a component library aimed at the AI-app UI wave.
beautifului.dev ↗A Zig code-intelligence server and MCP toolset for AI agents, recommended firsthand by the sharer. Native-speed code intelligence as agent context is a strong pitch.
github.com/justrach/codedb ↗Persistent semantic memory for coding agents — an MCP server that indexes your codebase. Useful when you have many repos and context windows aren't enough.
github.com/DeusData/codebase-memory-mcp ↗A JavaScript runtime for the BEAM — Web APIs backed by OTP, native DOM, and a built-in TypeScript toolchain. Genuinely novel: Erlang's concurrency model meets JS.
github.com/elixir-volt/quickbeam ↗Unsloth's GGUF quantization of Qwen3.6-27B with MTP (multi-token prediction). For local inference of the 27B Qwen.
huggingface.co/unsloth/Qwen3.6-27B-MTP-GGUF ↗Alibaba's announcement that Qwen3.8's open weights are out. Announcement-only; pair with the unsloth GGUF quant below for local runs.
x.com/alibaba_qwen/status/2088280182356611304 ↗Unsloth's GGUF quantization of Qwen3.8-27B for local inference. The practical artifact behind the open-weights announcement above.
huggingface.co/unsloth/Qwen3.8-27B-GGUF ↗A JetBrains IntelliJ ACP (Agent Client Protocol) adapter for the pi coding agent. Niche but exactly what you need if you want pi inside IntelliJ.
github.com/ryan-brosas/pi-acp-jetbrain ↗Woxi's comparison of itself against Mathematica — Woxi being an interpreter for a subset of the Wolfram Language. A decent way into what Woxi is and where it stands.
woxi.ad-si.com/docs/comparison/mathematica ↗GitHub's official toolkit for spec-driven development — write the spec, let agents implement. From GitHub itself, so it carries weight in the SDD workflow trend.
github.com/github/spec-kit ↗An open-source, model-agnostic, BYOK GitHub bot that runs in GitHub Actions. Bring your own key, pick your model, automate your repo — the self-hosted answer to proprietary coding agents.
github.com/pullfrog/pullfrog ↗DeepSeek's agent harness in developer preview — "everything is a plugin", with source released alongside. Every agent capability is a swappable plugin; the plugin architecture is the interesting idea here.
deepseek.com/harness/en ↗A multiplayer environment for coding with agents — shared threads where teammates and agents build and review together, with full conversation and code context.
delta.dev ↗The Rust Foundation's quality standard for Rust training. Reference material if you're evaluating Rust courses or building one.
rustfoundation.org/rust-foundation-trusted-training ↗Turso's introduction to AgentFS, which Rykuuun found interesting.
docs.turso.tech/agentfs/introduction ↗Rykuuun shared this asking "this is pi-vcc right?", suggesting it's related to a "pi" coding agent with very large context.
github.com/ranxianglei/billion-context-pi ↗A 2020 article by Daniel Rotter arguing for CSS layouts that avoid z-index.
danielrotter.at/2020/04/08/avoid-z-index-whenever-p… ↗A GitHub repo, likely a motion/animation library given the name.
github.com/oil-oil/oil-motion ↗A directory of open-source alternatives to popular software.
thereisanopensourceforthat.com ↗An agent skill themed on Linus Torvalds, presumably encoding his review style for code agents.
github.com/Mte90/linus-torvalds-skill ↗Artificial Analysis's model page for Qwen3-8 Max, with benchmarks and pricing.
artificialanalysis.ai/models/qwen3-8-max ↗A Wafer blog post benchmarking Kimi K3 on AMD MI355X hardware.
wafer.ai/blog/kimi-k3-mi355x ↗An MLX port of moonshotai's Kimi-K3 (2.78T multimodal MoE); the weights are converted from the original release and requantized.
github.com/PipeNetwork/kimi-k3-mlx ↗A self-hosted AI agent console ("Tu agente AI self-hosted") that thelaggingway is giving a go.
hermes.xpetalab.dev ↗A free, framework-free AI chat UI kit for AI projects.
github.com/vojtasve-droid/nimbus-lite ↗A desktop app that generates 3D models from images using local AI.
github.com/lightningpixel/modly ↗Rebuilds the object in a reference image as code-only procedural Three.js.
github.com/hoainho/img2threejs ↗Shared without description; the name suggests an OpenAI-compatible server with context compaction for the pi agent.
github.com/algal/pi-openai-server-compaction ↗Plasma AI's Fractal wraps Claude Code and Codex in bounded recursive loops.
plasma.ai/research/fractal ↗Static checks for ordinary TypeScript layout code, from chenglou.
github.com/chenglou/freerange ↗A Cursor-style visible follow-up queue with inline editing for the Pi agent.
github.com/tmustier/pi-queue-steer ↗Use your x.com Premium/SuperGrok subscription in pi with OAuth login, auto-refresh, and live model discovery; supports grok-4.5, grok-composer-2.5-fast, grok-build, grok-4.3, and x_search.
github.com/stnly/pi-grok ↗A vendor verifier from MoonshotAI; baanish asked if anyone has run it.
github.com/MoonshotAI/Kimi-Vendor-Verifier ↗An agentic coding setup that Rykuuun found "more flexible" than alternatives.
github.com/Dicklesworthstone/agentic_coding_flywhee… ↗A proxied shell + exit-node picker for Tailscale userspace networking, with egress through Mullvad or other providers.
github.com/monotykamary/tailscale-shell ↗Docker & Linux containers native to Mac — free, open source, one shared VM for all containers, claiming ~4.7x less idle memory than per-container setups.
augani.github.io/dory ↗An agent skill that generates beautiful architecture diagrams with dark/light theme toggle and PNG/JPEG export.
github.com/tt-a1i/archify ↗A fast Rust port of Steve Yegge's beads — a local-first, non-invasive issue tracker storing tasks in SQLite. Rykuuun "really loved this tool" and says it makes things easier to manage.
github.com/Dicklesworthstone/beads_rust ↗A loop library from ForwardFuture Signals, shared as a design reference.
signals.forwardfuture.ai/loop-library ↗Flue 1.0 Beta announcement — "the open framework for building agents without lab lock-in: write once, deploy..." Details beyond the embed preview are unverified.
flueframework.com/blog/flue-1-0-beta ↗"Supercharge Your LLM with the Fastest KV Cache Layer." The performance claim is the project's and unverified.
github.com/LMCache/LMCache ↗Use Claude Code, Codex, and Gemini CLI through the Agent Client Protocol (ACP) inside pi.
github.com/junghan0611/pi-shell-acp ↗A fix by monotykamary — diff.print() (default Patch format) was stripping the +/-/space line-origin prefixes from output; this PR prepends them back.
github.com/toss/es-git/pull/213 ↗A validate-then-repair extension for pi that fixes common LLM tool-call mistakes (null fields, stringified arrays, wrong field names, anchor bleed) before tools execute. Tom: "technically their tool repair brought over to pi (+ my additions)."
github.com/monotykamary/pi-tool-repair ↗A fix for fff — the /fff-mode override was only stored in an in-memory variable lost on /reload and session restart; this PR persists fff-mode across reloads and session resumes.
github.com/dmtrKovalenko/fff/pull/593 ↗"The fastest and the most accurate file search toolkit for AI agents, Neovim, Rust, C, and NodeJS." The performance claim is the project's and unverified.
github.com/dmtrKovalenko/fff ↗Analyze coding (agent) CLI token usage and costs from local data.
github.com/ryoppippi/ccusage ↗Generate HD short videos with one click using AI LLMs (the repo description is in Chinese).
github.com/harry0703/MoneyPrinterTurbo ↗MiniMax's M3 announcement — frontier coding capability, 1M context, native multimodality, and a new MSA architecture.
minimax.io/blog/minimax-m3 ↗A Codex/ChatGPT multiple-account load balancer and proxy with usage tracking, a dashboard, and OpenCode compatibility. Tom: "gonna try first."
github.com/Soju06/codex-lb ↗"Built to extend you. 10× your day" — an AI extension of you across every device and person: takes your calls, writes your emails, and more.
zinley.com/self-audit ↗What #share-tech has been sharing: volume, category mix and the most active sharers across 15 weeks.
Curated resources added each week, oldest to newest.
Most prolific link-sharers in the channel.
How the category mix shifted across weeks.
Share of each category across all 184 resources.
What the top sharer shares most.
Tom · 82 resources shared