docs: launch-ready README + GPLv3 LICENSE - #144
Merged
Conversation
Replace the bare setup notes with a marketing-ready, technically-accurate README: hero + badges, a tweet-able hook, a fact-checked feature list (real ACP agents, MCP relay, Daytona sandboxes, workspaces, sharing, rewind/fork, usage limits), a "How it works" architecture diagram (Convex realtime + FastAPI gateway + ACP-in-Daytona + MCP relay), an accurate tech-stack table, a preserved-and-corrected quickstart, and the monorepo layout. Every technical claim was verified against source (versions, the 19-table schema, agent launch specs, OAuth/DCR details, CI). Add the verbatim GNU GPLv3 license text as LICENSE and a License section.
Code reviewNo issues found. Checked for bugs and CLAUDE.md compliance. |
Reworks the README per review: removes all feature-section emojis and the
per-bullet file:line citations (less "AI slop", more scannable); leads with the
share/collaboration story ("Share a chat. They drive your agent. You watch
live." — editors run turns on the OWNER's harness/credentials/billing);
rewrites the "How it works" ASCII diagram cleanly and folds in the Redis Streams
live-follow (tee → per-conversation stream → blocking XREAD fan-out to
followers, allowlist/sanitize, fail-soft). Drops the outdated product
screenshot. Fact-checked against source.
Replaces the removed/outdated preview with fresh shots taken against a live deployment running ENABLE_DEV_AUTH: a coding-agent session in a workspace (banner) and the share dialog under the collaboration section.
Restructures the README screenshots per review: a single characteristic shot of the chat app (an agent doing real work — MCP doc lookup, terminal build with an "exit 0", file edit, a subagent, and a Workflow card, in a colored workspace) sits at the top; everything else moves into a collapsed <details> gallery (subagent + workflow card, Context7 MCP connected, harnesses grouped by status, the harness editor, the share dialog). Drops the older chat-view.png. Captured loginless via dev-auth against a real deployment with seeded data.
Code reviewNo issues found. Checked for bugs and CLAUDE.md compliance. |
Drove a live Claude Code agent (in a real Daytona sandbox) and captured genuine output, replacing the previously-seeded transcript mockups: - hero: a real session exploring a sandbox — actual tool calls, a terminal run with exit 0, and the real result (node v22.22.3, primes 2..29). - background-agents panel with two real subagents running in parallel. - a multi-step run showing the plan, edits, and a passing test suite. - an approval card from a real run (the agent asking before a write). Keeps the MCP / harnesses / harness-edit / share shots. Hero stays at the top; the rest remain in the collapsed gallery.
Cut the Features section to ~a third — name each feature, drop the specifics.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
README.mdfrom bare setup notes into a public, marketing-ready and technically-accurate document — modeled structurally on a clean reference README (hero + badges → hook → features → how-it-works → tech stack → quickstart → layout → license).LICENSE— the verbatim GNU GPLv3 text (fetched from gnu.org), plus a License section + copyright line in the README.Accuracy
This was written research-first and adversarially fact-checked against source. Notable corrections caught and applied during review:
grepcounted thedefineTableimport line).cursor-agent --force acp(the--forceflag matters).session_manager.py(the route lines are the answer endpoints).AGENT_CREDENTIALS_KEYisn't in.env.example;FRONTEND_URLshould be:3000to match the web dev port; CI runs vitest for frontend + Convex (not just frontend).All versions verified verbatim from
package.json/registry.py(Bun 1.3.5, TS 5.9.2, Convex 1.31.7, React 19, TanStack 1.132, codex-acp 0.16.0, claude-agent-acp 0.44.0, …).Notes
harness-landing-full-page.png, already tracked) is a 2880×7902 full-page capture — too tall for a hero, so it's behind a collapsible Product preview<details>. A proper logo/banner asset (assets/logo.png) could replace the text hero later.🤖 Generated with Claude Code