Meta tags:
description=The best agent harness. Contribute to mindfold-ai/Trellis development by creating an account on GitHub.;

Headings (most frequently used words):

uh, oh, navigation, resources, saved, searches, trellis, use, to, files, history, how, footer, search, code, repositories, users, issues, pull, requests, provide, feedback, mindfold, ai, menu, filter, your, results, more, quickly, folders, and, latest, commit, repository, why, prerequisites, quick, start, it, works, faq, star, community, about, releases, packages, contributors, languages, topics, license, contributing, stars, watchers, forks,

Text of the page (most frequently used words):
#trellis (33), the (27), and (25), your (15), github (14), code (14), security (10), you (9), workflow (9), specs (9), use (8), agents (8), session (8), all (8), reload (7), start (7), from (7), context (7), platform (7), with (7), view (7), can (6), this (6), docs (6), license (6), agent (6), spec (6), for (6), claude (6), files (6), enterprise (6), community (5), navigation (5), while (5), contributing (5), resources (5), coding (5), issues (5), workspace (5), repo (5), teams (5), memory (5), task (5), platforms (5), check (5), name (5), search (5), time (4), there (4), was (4), error (4), loading (4), please (4), page (4), readme (4), codex (4), mindfold (4), project (4), then (4), works (4), see (4), quick (4), sub (4), type (4), auto (4), commit (4), implement (4), skills (4), work (4), json (4), pnpm (4), yaml (4), actions (4), support (4), packages (3), repository (3), stars (3), agpl (3), harness (3), topics (3), app (3), best (3), journals (3), developer (3), shared (3), tasks (3), they (3), any (3), write (3), every (3), developers (3), standards (3), how (3), supported (3), install (3), runs (3), new (3), into (3), starts (3), writes (3), prd (3), one (3), research (3), what (3), cursor (3), opencode (3), team (3), last (3), more (3), marketplace (3), open (3), insights (3), pull (3), requests (3), signed (3), settings (3), another (3), tab (3), window (3), refresh (3), sign (3), saved (3), documentation (3), feedback (3), grade (3), features (3), copilot (3), solutions (3), explore (3), that (2), personal (2), manage (2), status (2), footer (2), other (2), python (2), tags (2), releases (2), forks (2), 694 (2), official (2), blog (2), star (2), history (2), stay (2), per (2), where (2), when (2), keep (2), file (2), solo (2), benefit (2), but (2), prds (2), changelog (2), track (2), templates (2), real (2), finish (2), against (2), lint (2), tests (2), curated (2), injected (2), requirements (2), question (2), items (2), result (2), jsonl (2), brainstorm (2), plan (2), let (2), clear (2), implementation (2), setup (2), latest (2), init (2), initialize (2), instead (2), each (2), review (2), conventions (2), changes (2), why (2), cases (2), engineering (2), out (2), pyrightconfig (2), lock (2), package (2), readme_cn (2), copyright (2), contributing_cn (2), lintstagedrc (2), gitmodules (2), gitignore (2), c9a1918 (2), drafts (2), site (2), 899217e (2), assets (2), omp (2), husky (2), 181 (2), commits (2), message (2), menu (2), quality (2), projects (2), discussions (2), appearance (2), cancel (2), available (2), searches (2), repositories (2), business (2), advanced (2), source (2), customer (2), services (2), devops (2), perform, action, not, share, information, cookies, contact, privacy, terms, 2026, inc, javascript, typescript, languages, contributors, 133, report, watching, watchers, custom, properties, activity, agentic, claudecode, trytrellis, about, built, tech, discord, yes, separate, reviewed, improved, like, artifact, without, constant, conflicts, many, letting, draft, existing, tighten, important, parts, hand, high, signal, rules, explicit, versioned, have, manually, both, repeatable, get, larger, boundaries, reviewable, portability, layer, across, multiple, ides, only, those, are, useful, entry, points, tend, become, monolithic, adds, scoped, gates, aware, generated, around, them, different, cursorrules, faq, world, scenarios, practice, understand, differences, link, need, final, promotes, learnings, back, next, smarter, update, reviews, diff, self, fixing, verify, git, walks, through, heavy, referenced, phase, loop, invoked, done, fills, archives, updates, calls, checks, run, until, begins, natural, language, describe, want, simple, guides, details, npm, mindfoldhq, actually, node, prerequisites, bring, same, structure, rebuilding, tool, multi, live, person, hard, won, rule, whole, preserve, happened, stays, structured, centered, once, inject, relevant, repeating, yourself, capability, 简体中文, fast, scratch, persists, box, framework, date, folders, branches, main, additional, options, fork, must, change, notification, notifications, public, dismiss, alert, switched, accounts, resetting, focus, create, qualifiers, our, query, filter, results, quickly, submit, include, email, address, contacted, read, piece, take, input, very, seriously, provide, syntax, tips, users, jump, pricing, premium, add, ons, powered, collections, trending, archive, program, accelerator, maintainer, lab, programs, fund, sponsors, partners, trust, center, forum, ebooks, reports, events, webinars, stories, software, development, topic, industries, government, manufacturing, financial, healthcare, industry, devsecops, modernization, case, nonprofits, startups, small, medium, enterprises, company, size, stop, leaks, before, secret, protection, secure, build, find, fix, vulnerabilities, application, instant, dev, environments, codespaces, automate, workflows, integrate, external, tools, mcp, registry, direct, issue, merge, better, creation, toggle, skip, content,

Text of the page (random words):
github mindfold ai trellis the best agent harness github skip to content navigation menu toggle navigation sign in appearance settings platform ai code creation github copilot write better code with ai github copilot app direct agents from issue to merge mcp registry new integrate external tools developer workflows actions automate any workflow codespaces instant dev environments issues plan and track work code review manage code changes application security github advanced security find and fix vulnerabilities code security secure your code as you build secret protection stop leaks before they start explore why github documentation blog changelog marketplace view all features solutions by company size enterprises small and medium teams startups nonprofits by use case app modernization devsecops devops ci cd view all use cases by industry healthcare financial services manufacturing government view all industries view all solutions resources explore by topic ai software development devops security view all topics explore by type customer stories events webinars ebooks reports business insights github skills support services documentation customer support community forum trust center partners view all resources open source community github sponsors fund open source developers programs security lab maintainer community accelerator github stars archive program repositories topics trending collections enterprise enterprise solutions enterprise platform ai powered developer platform available add ons github advanced security enterprise grade security features copilot for business enterprise grade ai features premium support enterprise grade 24 7 support pricing search or jump to search code repositories users issues pull requests search clear search syntax tips provide feedback we read every piece of feedback and take your input very seriously include my email address so i can be contacted cancel submit feedback saved searches use saved searches to filter your results more quickly name query to see all available qualifiers see our documentation cancel create saved search sign in sign up appearance settings resetting focus you signed in with another tab or window reload to refresh your session you signed out in another tab or window reload to refresh your session you switched accounts on another tab or window reload to refresh your session dismiss alert message uh oh there was an error while loading please reload this page mindfold ai trellis public notifications you must be signed in to change notification settings fork 694 star 12 4k code issues 14 pull requests 3 discussions actions projects security and quality 0 insights additional navigation options code issues pull requests discussions actions projects security and quality insights mindfold ai trellis main branches tags go to file code open more actions menu folders and files name name last commit message last commit date latest commit history 1 181 commits 1 181 commits agents skills agents skills claude claude codex codex cursor cursor github github husky husky omp omp opencode opencode pi pi trellis trellis assets assets docs site 899217e docs site 899217e drafts drafts marketplace c9a1918 marketplace c9a1918 packages packages gitignore gitignore gitmodules gitmodules lintstagedrc lintstagedrc agents md agents md claude md claude md contributing md contributing md contributing_cn md contributing_cn md copyright copyright license license readme md readme md readme_cn md readme_cn md package json package json pnpm lock yaml pnpm lock yaml pnpm workspace yaml pnpm workspace yaml pyrightconfig json pyrightconfig json view all files repository files navigation readme contributing agpl 3 0 license more items an out of the box engineering framework for ai coding ai writes code fast but every session it starts from scratch no memory of your project your conventions or your team s requirements trellis persists specs tasks and memory into your repo so any coding agent works to your engineering standards 简体中文 docs quick start supported platforms use cases why trellis capability what it changes auto injected specs write conventions once in trellis spec then let trellis inject the relevant context into each session instead of repeating yourself task centered workflow keep prds implementation context review context and task status in trellis tasks so ai work stays structured project memory journals in trellis workspace preserve what happened last time so each new session starts with real context team shared standards specs live in the repo so one person s hard won workflow or rule can benefit the whole team multi platform setup bring the same trellis structure to 17 ai coding platforms instead of rebuilding your workflow per tool prerequisites node js 18 python 3 9 quick start 1 install trellis npm install g mindfoldhq trellis latest 2 initialize in your repo trellis init u your name 3 or initialize with the platforms you actually use trellis init cursor opencode codex u your name see the quick start and supported platforms guides for setup details how to use the workflow is simple describe what you want in natural language brainstorm with the ai one question at a time until the prd is clear then implementation begins let it run the ai calls trellis implement and auto checks the result against specs lint type check and tests type trellis finish work when the work is done or the session context fills up trellis archives the task and updates journals how it works trellis runs a 4 phase loop with auto invoked skills and sub agents plan trellis brainstorm walks through requirements one question at a time and writes prd md research heavy items go to a trellis research sub agent the result is curated specs research files referenced from implement jsonl check jsonl implement a trellis implement sub agent writes code from the prd with the curated context auto injected no git commit verify a trellis check sub agent reviews the diff against specs and runs lint type check and tests self fixing where it can finish a final check runs then trellis update spec promotes new learnings back into trellis spec so the next session starts smarter resources need link install trellis in a repo quick start understand platform differences supported platforms see the workflow in practice real world scenarios start from spec templates spec templates track releases changelog faq how is trellis different from claude md agents md or cursorrules those files are useful entry points but they tend to become monolithic trellis adds scoped specs task prds workflow gates workspace memory and platform aware generated files around them is trellis only for claude code no trellis is a project layer that works across multiple coding agents and ides is trellis for solo developers or teams both solo developers use it for memory and repeatable workflow teams get the larger benefit shared standards task boundaries reviewable context and platform portability do i have to write every spec file manually no many teams start by letting ai draft specs from existing code and then tighten the important parts by hand trellis works best when you keep the high signal rules explicit and versioned can teams use this without constant conflicts yes personal workspace journals stay separate per developer while shared specs and tasks stay in the repo where they can be reviewed and improved like any other project artifact star history community resources official docs github issues discord tech blog official repository agpl 3 0 license built by mindfold about the best agent harness docs trytrellis app topics harness codex ai workflow claudecode agentic coding resources readme license agpl 3 0 license contributing contributing uh oh there was an error while loading please reload this page activity custom properties stars 12 4k stars watchers 30 watching forks 694 forks report repository releases 133 tags packages 0 uh oh there was an error while loading please reload this page contributors uh oh there was an error while loading please reload this page languages typescript 68 4 python 25 5 javascript 5 2 other 0 9 footer 2026 github inc footer navigation terms privacy security status community docs contact manage cookies do not share my personal information you can t perform that action at this time