GitHub projects I’ve starred, and what each one adds to the state of the art. Repos are grouped into themes, and every review links to the repos it builds on or competes with.
GitHub projects I’ve starred, and what each one adds to the state of the art. Repos are grouped into themes, and every review links to the repos it builds on or competes with.
96 items under this folder.
Each theme is a running summary of one area: the main approaches, what each repo added, and the gaps. It's rewritten whenever a new repo joins.
Installable skill packs, plugins and working methods that change how a coding agent works. The approaches differ in what they package: a loose set of skills, domain taste, a fixed development process, or prompts for structured thinking.
Main approaches: Skill collections, Domain skills, Development methodologies, Structured reasoning lenses
16 repos · updated Oct 26, 2026 · Read the theme →
Workspaces, IDEs and platforms where several coding or business agents, or agents and people, run side by side. The approaches differ in where the work lives: a desktop app with a Git worktree per task, a shared channel or repo, or a cloud reference platform.
Main approaches: Agent IDEs, Shared workspaces, Platforms on AWS
12 repos · updated Oct 27, 2026 · Read the theme →
Frameworks and reference stacks for building one agent: its loop, tools, state and runtime. The approaches differ in what they build on: a ready coding agent, an event log, plain conversation history, a per-task tuned harness, or a formal theory of composing components.
Main approaches: Harness frameworks, Composition research
10 repos · updated Oct 29, 2026 · Read the theme →
Libraries, stores and models that give agents memory or durable state across sessions. The approaches differ in where memory lives: a prompt and script, a storage backend, a context database, a trained model, or a normalized session record.
Main approaches: Memory prompts and scripts, Storage backends, Context databases, Context models, Session trajectories
10 repos · updated Oct 26, 2026 · Read the theme →
Languages, auditing tools, creative-coding libraries and personal utilities for people who make software and things. Approaches range from browser canvas libraries and web-page auditors to a new compiled language, a polyglot runtime, and small desktop and server tools.
Main approaches: Languages, Web auditing, Creative coding, Personal utilities, Hardware
10 repos · updated Oct 18, 2026 · Read the theme →
Benchmarks, leaderboards, and research environments that measure how well agents or models do defined work. Approaches range from domain task suites and harness comparisons to decision-model scoring and multi-agent simulations.
Main approaches: Harness benchmarks, Domain task benchmarks, Decision-model scoring, Research environments
8 repos · updated Oct 13, 2026 · Read the theme →
Software that stores, moves, encodes or produces data, from distributed key-value stores and object-storage databases to ELT connectors, protobuf codecs and synthetic document generators. The approaches differ in what they handle: data at rest, data in motion, data on the wire, or data made up on purpose.
Main approaches: Databases, Data movement, Encodings, Synthetic data
8 repos · updated Oct 27, 2026 · Read the theme →
Tools and samples for running models on your own hardware or in your own cloud account. The approaches differ in what you take on: scheduling GPU capacity, running a model server, using a packaged local app, or calling hosted models from cloud notebooks.
Main approaches: Compute schedulers, Model serving, Local AI apps, Cloud model samples
7 repos · updated Oct 26, 2026 · Read the theme →
Policy languages, sandboxes and security tooling that limit what an agent may do or check what it builds. Approaches range from static scanning pipelines and browser-level session binding to runtime policy engines that reason over an agent's action history.
Main approaches: Policy languages, Sandboxes, Security review tools
6 repos · updated Oct 13, 2026 · Read the theme →
MCP servers, CLIs, and discovery specs that give an agent a callable capability or let it find one across networks. Approaches split between domain-specific tool wrappers and the plumbing that connects agents to those tools.
Main approaches: MCP servers, Discovery protocols
4 repos · updated Oct 10, 2026 · Read the theme →
Small models that make one typed decision or classification instead of calling a full LLM. Approaches split between task-specific classifiers, general-purpose decision models, and ecosystem indexes around a single model.
Main approaches: Decision models, Ecosystems, Task-specific classifiers
3 repos · updated Oct 10, 2026 · Read the theme →
94 repos
What's new: It pairs an agent harness with a shared plugin system, so the author's apps (notes, maps, design tool, file explorer) reuse the same building blocks and an improvement to one shows up in the others.
A self-evolving personal OS
What's new: It treats the harness as something to optimize, proposing edits, probing them on the same task, and composing a refined harness from the contrasts, with no ground-truth feedback.
What's new: It wraps whatever CLI agent you already pay for in one desktop app, with a Git worktree, terminals, diff viewer and browser preview per task, plus a CLI, SDK and MCP server so agents can drive it too.
Paradev (formerly Superset) is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
What's new: It runs point-in-polygon queries, spatial joins and great-circle distances on the Apple silicon GPU through MLX, and can return results as MLX arrays to feed a model directly.
GPU-accelerated geospatial operations for Apple silicon, built on MLX
What's new: It is a single README that lays out a whole research stack in layers (Chronicle storage, Membrane for multi-participant LLM calls, context-manager, agent-framework) and says which app sits on which layer.
Research infrastructure overview for Anima Labs
What's new: It ships one prompt built around a ladder the agent climbs before writing code: does it need to exist, is it already in the codebase, does the standard library or a native platform feature do it, then the minimum that works.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
What's new: It installs as a skill inside whichever agent you already use, then selects, runs in parallel and verifies work across the locally installed agent CLIs, instead of being another agent itself.
AutoSwarm: All Your Agents, Working as One (Codex · Claude Code · DeepSeek Harness · Muse · Grok · WorkBuddy· nanobot · and more)
What's new: Its agents run slow tools concurrently and yield while they wait, and between turns an agent is pure data, just its conversation history, so a sleeping agent costs nothing until the next event.
An agent runtime and tool protocol for principled agent concurrency
What's new: Agents coordinate without a central orchestrator: each gathers context, claims a sub-task, takes action, verifies results and merges progress asynchronously, through a Gitea workspace, Mattermost messaging and a shared context mechanism.
A Decentralized, Scalable Multiagent Harness
What's new: It builds several databases (buffer, log, timeseries, vector) on one shared object-store storage layer, SlateDB, and one set of operational tooling.
OpenData is a collection of open source databases built on a common, object-native storage and infrastructure foundation.
What's new: It adds expression and camera control to an existing video diffusion model through a small adapter, with a distilled 4-step student that streams videos of any length.
Official Code for "Video Diffusion Avatars: Taming Video Diffusion Models into Controllable 3D Avatars"
What's new: It organizes memory into world facts, experiences, observations and mental models, and a background process consolidates stored facts into evidence-backed beliefs instead of leaving a flat pile.
Hindsight: Agent Memory That Learns
What's new: This skill has the agent place every node on a 4px grid with CI overlap checks and applies an opinionated editorial style pulled from your own website's palette and fonts.
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
What's new: Goose ships as a native desktop app, a full CLI, and an embeddable API in one Rust release, with 15+ provider backends and 70+ MCP extensions.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
What's new: memelint applies ASD-STE100, a controlled-language standard, to the prose embedded in source files, reporting violations by rule number with approved alternatives.
memelint lints the words that spread through comments, docstrings, and documentation
What's new: The repo structures a personal computing environment as a Bun plugin workspace, with Claude memory directories and MCP configuration sitting alongside app plugins rather than bolted on externally.
A self-evolving personal OS
What's new: Pi ships deliberate gaps (no sub-agents, no plan mode) and expects you to fill them via extensions, skills, prompt templates and Pi packages distributed over npm or git.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
What's new: Rather than bundling integrations into the agent core, it ships each one as an independently versioned directory installed at a reviewed catalog pin, so a Spotify fix ships without waiting for a Hermes release.
☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.
What's new: DeckWerk treats Linux as a first-class authoring platform and bakes in an agent-editing protocol where an AI agent mirrors the live deck folder and writes HTML slides that compile into normal editable objects, without a cloud service in the loop.
What's new: IMPRINT adds a pluggable memory encoder (full-attention or recurrent) that sits between episode history and an existing VLA policy backbone, using a two-stage recipe that first bootstraps the memory encoder alone, then adapts it together with the policy.
What's new: Elide provides a single runtime and toolchain that executes Kotlin, JavaScript, TypeScript, and Python together.
fast multi-lang runtime
What's new: Feather ships a single harness with two built-in profiles, prod and train, so the same agent loop and tools serve both live knowledge work and training rollout collection.
Feather agent harness, training integrations, and evaluation tools for knowledge work
What's new: It chains AI stem separation, multilingual lyric alignment with Cantonese jyutping and Japanese furigana, and a real-time web queue into one self-hosted pipeline you run on your own hardware.
一个包含地球上所有能唱的歌的免费KTV
What's new: This corpus normalises state statutes, regulations, court rules, constitutions, and AG opinions across dozens of US jurisdictions into one 27-column Parquet schema with quarterly dated snapshots, filling the gap left by the absence of open bulk state code data.
Open, structured corpus of US primary law: 2M+ sections of state statutory codes, the US Code, and state constitutions, plus the ingestion pipeline that builds it. Data on Hugging Face (CC BY 4.0); scrapers Apache-2.0. Quarterly snapshots.
What's new: PHP breaks long-horizon humanoid locomotion into three stages: offline motion matching to compose skill sequences, privileged-state RL teacher training, then depth-sensor student distillation via DAgger + RL.
[RSS 2026] Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
What's new: Compound Writing applies the installable-skill pattern to prose by separating voice rules (VOICE.md) from editorial standards (STYLE.md) and routing work through a context-aware front door skill, `cw-scribe`, rather than a fixed pipeline.
Proposed external architecture for Compound Writing, including public core and optional editorial edition boundary.
What's new: Instead of appending full conversation history, MEM1 trains a model via reinforcement learning to maintain a compact internal state that merges prior memory with new observations at each turn.
MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents. Accepted at ICLR 2026; Best Paper Award at the NeurIPS 2025 MTI-LLM Workshop.
What's new: EdgeQuake packages the LightRAG graph-retrieval algorithm as a single Rust binary backed only by PostgreSQL, adding multi-tenant auth, a web UI, an MCP server, and explicit versioned migrations.
EdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation
What's new: DBSC moves session refresh into the browser, so the server only needs changes at the sign-in handler and a dedicated refresh endpoint, while other parts of the site keep using cookies as before.
Device Bound Session Credentials: A Protocol for Protecting From Cookie Theft
What's new: CEO-Bench measures long-horizon planning by embedding the agent inside a 500-day business simulation with delayed consequences, partially observable state, and LLM-driven customer and social-media simulators.
CEO-Bench: Can Agents Play the Long Game?
What's new: Each entry ships the exact prompts, settings and hooks that DevRel actually used, plus a README explaining what failed before the setup worked.
What's new: claude-kit pairs a planning-and-delegation skill (savvy-flow) with a UI mod (savvy-progress) that renders a progress bar and agents panel inside Claude Code, letting you watch tiered worker subagents as they run.
Public Claude Code skills and mods
What's new: The skills encode specific aesthetic judgments about animation curves, motion performance, and UI micro-decisions that agents tend to get wrong, packaging that domain expertise as discrete Markdown files an agent can install.
Skills for Designers and Engineers.
What's new: Rather than caching answers or fine-tuning, Recur treats repetition as a supervision signal and compiles a verified, typed dataflow program via best-first search over a small IR, so subsequent answers run in under a millisecond with no model call.
What's new: A local Bash picker draws from 36 operators, 25 organons and 29 dimension prompts, producing a different method combination on each invocation with no network call required.
A Claude Code skill for expanding ideas via Patrick Gunkel's ideonomy, synthesized from Grace Kind's essays. Picks a different combination of operators, organons, and dimension-prompts each invocation.
What's new: Moondream offers a 0.5B distillation variant alongside its 2B model, keeping image understanding viable on resource-constrained hardware.
tiny vision language model
What's new: Φ-Bench targets ML systems work specifically: CUDA kernels, distributed training, vLLM serving, quantization, and MoE routing, each task scored offline inside a self-contained Docker image.
Phi-Bench (Φ-Bench): 85 open-source LLM-infrastructure engineering tasks for frontier LLMs & coding agents (KFC/LH/E2E). Self-contained public Dockerfile + offline scoring + reference solution per task. Website: llminfrabench.com
What's new: It closes the loop from live trace collection through dataset curation, fine-tuning, and OpenAI-compatible inference serving inside a single platform, so you don't wire those stages together yourself.
The platform for continuously improving AI agents.
What's new: c11 makes every panel scriptable over a socket so agents can split areas, spawn sub-agents, drive an embedded browser, mail agents across workspaces, and broadcast status to a sidebar.
Agent-native Terminal Multiplexing for 10,000x hyperengineers
What's new: Goose eliminates the heap entirely: all dynamic memory lives on bump-pointer stacks, so freeing any structure costs one store and references into growing arrays stay valid without lifetime annotations.
The Goose Programming Language
What's new: PixlPut tells windows of the same app apart by workspace path or document, and by open browser tab once you turn on an opt-in setting, so each window can return to its own saved spot.
What's new: Tasks target multi-step business workflows on local replicas of real commerce platforms, and each task passes only when every per-task verifier check clears against actual state changes in an isolated mock service.
CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
What's new: Airbyte pairs its ELT connector catalog with a separate Agent SDK that turns connectors into typed LLM tools for pydantic-ai, LangChain, OpenAI Agents, and FastMCP.
Open-source data movement for ELT pipelines and AI agents — from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.
What's new: OpenResearch adds literature grounding against alphaXiv, bioRxiv, and PubMed so agents can form informed hypotheses, and records every experiment in a local SQL database so agents can read past results before deciding what to try next.
Turn your coding agents into research agents
What's new: ARD defines a domain-anchored, federated discovery layer so agents can find callable resources across networks of discovery services.
Agentic Resource Discovery (ARD) specification
What's new: It maps the SDK's slash-separated key contract directly onto DynamoDB partition-plus-sort keys, with optional vector search, TTL expiry, and S3 offload for oversized values and no separate vector store.
Amazon DynamoDB storage backend for the Strands Agents SDK (TypeScript and Python): sessions, agent memory, semantic search over DynamoDB vector indexes, and S3 offload behind one Storage interface.
What's new: aws-bench provisions real, isolated AWS accounts, deploys CDK stacks into them, runs the agent with scoped credentials inside a container, and then scores the result with an LLM judge or a check of actual AWS resource state.
aws-bench measures how well AI agents and model combinations perform on real AWS work — diagnosing misconfigurations, provisioning infrastructure, and operating live cloud environments.
What's new: This repo collects AWS-hosted examples specifically for Anthropic Claude, covering prompt engineering, tool use with complex schemas, PDF knowledge bases with citations, Intercom classification and a multimodal Streamlit playground.
What's new: It offers two concrete compute paths, EKS with Helm or ECS plus Bedrock AgentCore Runtime, sharing the same agent interface and gateway layer, so teams can evaluate operational trade-offs against a working codebase.
A sample agentic ai platform to run agentic workflows on AWS using either EKS or Bedrock AgentCore with open source frameworks like LangChain/LangGraph, Strands, etc..
What's new: AVA covers the full lifecycle from business-case DCF models and operating-model selection through to compliance checklists for 14 frameworks, all surfaced in a single React/FastAPI control plane deployed on ECS Fargate.
A platfrom to Plan, Build, Operate, Secure, and Govern AI Systems for Financial Services on AWS
What's new: This collection has one Kimi K3 notebook for Amazon Bedrock and links to the Kimi API Platform on AWS Marketplace and to external SageMaker deployment examples.
Samples for getting started with Kimi models by Moonshot AI, on AWS
What's new: It treats document structure and tabular data as separate concerns: PDF-to-synthetic-HTML conversion runs through Bedrock Claude, while a four-stage pipeline (extract, schema, generate, test) splits paid schema extraction from free, offline, seeded row generation.
What's new: Rather than wrapping a single scanner, ASH orchestrates a roster of built-in security tools, normalizes all findings into SARIF/JSON/HTML, and exposes the whole pipeline as an MCP server so AI coding agents can trigger scans and read results directly.
ASH is an extensible, open source SAST, SCA, and IaC security scanner orchestration engine.
What's new: It structures threat modeling into nine phase-gated steps, from business context through residual risk and export, plus an optional code-validation step, with completion checks before export.
What's new: Buzz puts agents and humans in the same signed event log, using Nostr keypairs for identity, so every message, patch, CI result, and workflow step lands in one searchable audit trail rather than across separate tools.
A hive mind communication platform
What's new: Tardigrade derives durable agent state from an immutable event log through composable atoms, drawing on inspiration from Elm.
The TypeScript framework for building modular agents around an immutable event log.
What's new: Tastemaker uses runnable Python scripts (contrast checker, palette generator, anti-slop scanner) and writes decisions to local lock files so constraints enforce themselves across sessions and projects.
A Claude Code skill that grounds AI-generated UI in real reference images and a persistent per-developer taste profile, instead of generic AI-slop defaults.
What's new: OpenDots can give each agent its own isolated browser and file workspace that persists across restarts, then wires that computer into a document workspace where agents can draft, review, and save pages with a human-in-the-loop approval step.
Your always-on AI coworkers that move between text, calls, and Slack.
What's new: This repo points to a preprint that gives the formal calculus behind Cordis, grounding dynamic component composition in effect and coeffect theory with a metatheory that shows components can interleave without disturbing one another.
A Programming Paradigm for Spatiotemporal Composability
What's new: VoiceStudio bundles voice cloning, video dubbing, dictation, transcription, and audiobook generation into a single local desktop app with a GUI, a local API, and MCP support, defaulting to the k2-fsa/OmniVoice engine with other engines selectable from a built-in catalog.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
What's new: Where the Dogwood reference interpreter processes an entire event trace at once, this engine ingests events one at a time, checkpoints state to disk, and resumes correctly after a crash.
Implementation of an authorization engine for Dogwood policies
What's new: Dogwood extends Cedar's permit/forbid syntax with temporal predicates (formerly, since, windowed aggregations) so policies can reason over an agent's recent event history, not just the current request.
Reference parser and interpreter for the Dogwood policy language
What's new: CLMs treat the context as a file and give the model unrestricted write access to it, then improve that behavior with evolved natural-language instructions or online RL.
Official repository for "Context Language Models"
What's new: vllmops keeps model configs and project settings in Git-reviewable YAML files and pairs a scriptable CLI with a live Textual TUI, so you can drive the full vLLM lifecycle from both without Docker or a monitoring stack.
Self-hosted vLLM made simple. Git-friendly YAML for models and profiles, full lifecycle from an intuitive CLI and TUI.
What's new: It holds model, tasks, and runtime constant across nine harnesses to isolate harness-level effects on pass rate, cost, cache behavior, and speed, then ships a reproducible skill so a third party can evaluate their own harness on the same task set.
Public results and task definitions for FrontierHarness Eval
What's new: JevBench scores decision models on four axes: Intelligence (chance-corrected accuracy with a penalty below 50), Calibration (ECE and label-distribution fidelity), Speed (log-scale latency at p50 and p95), and Cost reported per 1,000 decisions rather than per 1,000 tokens.
JevBench by Benchmark Heaven: benchmark and leaderboard for AI decision models, measuring typed decision accuracy, calibration, latency and cost.
What's new: It adapts principles inspired by the ISO 24495 plain language series (unofficial, with no conformance claim) into agent-readable skill files and a rule engine that audits Markdown against measurable criteria: sentence length, paragraph length, legalese, heading depth, undefined acronyms, and more.
ISO 24495 Plain Language skills and plugin
What's new: Lighthouse splits its run into a separate gather phase and audit phase, letting you capture browser artifacts once and re-audit them offline without hitting the network again.
Automated auditing, performance metrics, and best practices for the web.
What's new: at_mcp gives the agent ownership of credentials, session, and a write quota, so it holds a persistent AT Protocol identity across runs.
An agent's own AT Protocol account, through MCP
What's new: It ships three interfaces in one repo: a standalone binary for humans, a Streamable HTTP MCP server for agents, and a self-generating Skill file that tells coding agents how to use the CLI commands.
A Command-Line Interface (CLI), Skill and MCP Server to interact with Papers with Code. For agents and humans.
What's new: Unicel stores each cell value as a (number, unit) tuple, making unit cancellation and metric/imperial conversion part of the formula engine rather than a manual step.
Unit-aware spreadsheet application with dimensional analysis
What's new: Alongside the human-readable entries, it maintains a machine-readable policy registry (policies.json) and a revocation list (revocations.json), both versioned in Git so tooling can consume them directly.
A curated list of software, simulators, policies, agent tools and coverage for the Pollen Robotics / Hugging Face Microduck robot
What's new: Kite wraps Jetstream V2 as an OTP-native behaviour module, letting you define a subscriber with compile-time collection filters and pluggable cursor callbacks rather than managing websocket state yourself.
An Elixir atproto Jetstream V2 subscriber library
What's new: The code includes OpenAI-powered scripts for generating idea chains, neologisms, and evaluating ideas, alongside curated text lists on topics like flowers, fractals, and cooperation.
What's new: SwarmWorld measures collective technological evolution at the society level: artifacts persist between ticks, executable programs are inherited by successors, the engine keeps causal knowledge records, and traces are deterministically replayable with counterfactual contributor-removal.
What's new: Trajectory parses raw session transcripts from 15 agent runtimes, each with its own incompatible format, into a single schema-validated record array that training, evaluation, analysis, and inference systems can consume.
Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)
What's new: pbf splits decoding and encoding into separate tree-shakeable classes and keeps the bundle at 2.5KB gzipped, with lazy decoding and a CLI that compiles `.proto` schemas into plain, editable JavaScript.
A low-level, lightweight protocol buffers implementation in JavaScript.
What's new: Loom derives every REST route, MCP tool, CLI command, and authority boundary from one Rust declaration per operation, so the server, the CLI, and the MCP adapter cannot disagree.
Issue tracking for AI coding agents
What's new: Each skill is a small, composable unit covering one job, so you pick the ones you want and leave the rest.
Skills for Real Engineers. Straight from my .agents directory.
What's new: Rather than wrapping a single analysis engine, REA dispatches across native decompilers, JavaScript/Electron inspection, .NET assembly reading, Android APK tools, firmware extractors, and browser capture through one MCP interface with evidence attached to every finding.
Reverse engineer anything with agents, from app behavior down to native binaries.
What's new: It is based on Patrick Gunkel's Ideonomy and runs as an engine with 28 named lenses, profile-based auto-selection, lens chaining, cross-lens synthesis, and persistent sessions.
Structured creative reasoning for AI agents. Systematic thinking through 28 ideonomic lenses. 🔬
What's new: Superpowers bundles an end-to-end development workflow, from requirements brainstorming through subagent-driven task execution and TDD enforcement, with skills that fire automatically in sequence.
An agentic skills framework & software development methodology that works.
What's new: This pack encodes UX and visual design judgment as agent-readable skills: when to use a specific research method, how to tokenize a design system, and what a heuristic evaluation should cover.
Designer Skills Collection: agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery.
What's new: p5.js carries Processing's setup/draw sketch model directly into the browser, treating the whole web page as your sketch.
p5.js is a client-side JS platform that empowers artists, designers, students, and anyone to learn to code and express themselves creatively on the web. It is based on the core principles of Processing. Looking for p5.js 2.0? http://beta.p5js.org
What's new: It ships a single compiled neural program identified by a fixed ID, downloaded once and then run locally for all subsequent inference.
Detect and type PII locally with one ProgramAsWeights neural program.
What's new: SkyPilot spans 20+ clouds, Kubernetes, and Slurm clusters under a single control plane, routing jobs to available capacity with automatic failover and bin-packing.
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
What's new: This pack encodes a business methodology, translating Sahil Lavingia's Minimalist Entrepreneur framework into ten sequenced Claude Code commands.
Based on The Minimalist Entrepreneur by Sahil Lavingia
What's new: Box ties OS-level sandboxing to a stateful Dogwood policy engine so a file read through one interpreter can block a later network request, and injects credentials into permitted outbound calls without exposing secrets to the agent process.
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon, with Linux support planned.
What's new: Strands Decider replaces its language-modelling head with a pointer head that scores options by comparing hidden states, producing calibrated confidence values without any generation loop.
A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.
What's new: Superset wraps any CLI coding agent in a full desktop IDE with per-worktree browser previews, a diff viewer, scheduled automations, and an MCP server that lets agents create and manage their own workspaces.
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
What's new: TiKV pairs classical raw key-value access with full ACID transactional semantics modeled after Google Percolator, giving applications a single store that handles both access patterns.
Distributed transactional key-value database, originally created to complement TiDB
What's new: Rather than a storage backend or vector database, OptMem stores memories as fixed-width append-only lines in a plain text log and builds a binary tree of summaries on top, so the agent navigates and compresses its own history with simple shell commands and no external dependencies.
Permanent memory for AI agents. A 426-token prompt, a script, plug and play.
What's new: OpenViking structures all context as a navigable filesystem under `viking://` URIs with scoped semantic search and three-tier summaries (abstract, overview, full content) so agents can judge relevance before reading.
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
What's new: It tracks a single model's ecosystem by requiring each entry to use Jev, or a documented Jev port or derivative, for a concrete decision task.
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.