Decision models still lead, joined by an org chart for agents, an Office SDK and a go-live skill

Fastest-growing this period

Counts come from GitHub's official stargazers/history endpoint: the stars gained on each day of the window. Project briefs and the reading notes below are editorial additions.

1. 1

   NandhaKishorM/laya : Answer typed questions about any text in one 33-millisecond forward pass

   Python

   A non-autoregressive decision engine that reads text, an email or a JSON document and returns a typed answer, a choice, a score or a yes/no flag, in one 33-millisecond forward pass. Three checkpoints cover English, over one hundred languages and typed workflows, and a built-in router picks one per request. Nothing is generated, so there is nothing to parse or hallucinate.

   +2,183
2. 2

   paperclipai/paperclip : Run a company of AI agents with org charts, tickets and per-agent budgets

   TypeScript

   An open-source control plane for running AI agents like a company. Tasks turn into tickets with approval and review gates you verify from diffs, screenshots and tests; an org chart gives every agent a role, a boss and scoped secrets; heartbeats wake agents on a schedule; and a monthly budget per agent stops runaway token spend. Any runtime that answers a heartbeat plugs in.

   +1,660
3. 3

   vectorize-io/hindsight : Agent memory with three operations: retain, recall, and reflect to keep learning

   Python

   An agent memory system organized around three operations: retain observations, recall them when needed, and reflect to keep what an agent knows up to date. Memory banks and mental models structure the knowledge, it runs as a Docker, pip or embedded Python service against 25+ LLM providers, and an MCP server plus a two-line LLM wrapper connect it to coding agents.

   +1,506
4. 4

   dream-num/univer : An embeddable Office SDK with sheets, docs and slides, headless for agents

   TypeScript

   A customizable Office SDK covering spreadsheets, documents and presentations. Canvas rendering and a dedicated formula engine keep large workbooks responsive, plugins compose or lazy-load capabilities, and one Facade API runs the same code in the browser and headless in Node.js, so agents can edit and verify Office files through structured APIs. Presets give a quick start.

   +1,468
5. 5

   google/ax : Declare agent tasks in YAML, sandbox them, then SSH into a running one

   Go

   A declarative orchestrator from Google for agent workloads on a cluster, in the spirit of Kubernetes. One YAML file declares the task, pre-wired Git repos and MCP servers, a network allowlist and the model; ax apply launches it into a sandbox with CPU and memory limits, and ax ssh opens a shell inside a running agent to watch what it does.

   +1,372
6. 6

   eternity4719/HowToLiveBetter : Life advice that logs what you spend, what you gain and how solid the evidence is

   HTML

   A Chinese guide of practical suggestions on health, money, scams and legal traps, from chronic disease and first aid to rent disputes and workplace compensation. Each entry records what you spend, what you get back and how strong the evidence is, citing only journal papers and official documents, with an online search page for quick lookups.

   +1,365
7. 7

   rohitg00/ai-engineering-from-scratch : Learn AI engineering by building and checking real projects

   Python

   A structured AI-engineering curriculum with routes for fundamentals, LLM applications and agents. It pairs reading with building and checking results, useful when you want to learn toward a working project instead of collecting disconnected tutorials.

   +1,039
8. 8

   mikehasa/golive-skill : Take an agent-built app live: hosting, database, auth, domain, email, payments

   TypeScript

   An open-source agent skill that takes a generated app to real users. It detects what your app needs, writes a plan and asks your approval, then provisions hosting, database, DNS, email, test-mode payments and auth on your own accounts, verifying each observable step. It records what it created, re-checks for drift, and teardown removes only what it can prove it created.

   +907
9. 9

   stablyai/orca : Compare several coding agents in separate workspaces

   TypeScript

   A desktop interface for running terminal coding agents in separate Git worktrees. You can compare attempts at the same task and inspect their changes, useful when juggling several experiments would otherwise mean managing many terminals and directories.

   +904
10. 10

    deepseek-ai/deepseek-harness : Explore DeepSeek's building blocks for an extensible agent

    TypeScript

    DeepSeek's agent runtime built around replaceable plugins, with a web interface for running it. Useful for developers exploring how to compose an agent's capabilities; it is a developer preview, so expect interfaces to change as you experiment.

    +884

Ranking window: 2026-09-24 UTC, full day.