Skip to content

docs(readme): drop bare agent count and framework name from prose #15

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
adbarc92 merged 1 commit into from
Aug 10, 2026
Merged

docs(readme): drop bare agent count and framework name from prose #15

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@

**A parallel, MCP-coordinated multi-agent engine that takes a product idea from clarification → design → code → test → deploy → iterate, run by independent worker processes with human approval gates and automatic budget control.**

AppForge models a ~14-person software team as **16 specialized agents** that a scheduler dispatches across a **six-phase dependency graph**. The orchestration is not a single async loop — it is a genuine **MCP state server** plus a pool of **independent OS worker processes** that claim and execute work concurrently, coordinating shared state without collision.
AppForge models a software team as a roster of **specialized agents** that a scheduler dispatches across a **six-phase dependency graph**. The orchestration is not a single async loop — it is a genuine **MCP state server** plus a pool of **independent OS worker processes** that claim and execute work concurrently, coordinating shared state without collision.

> **Status: v1.0 — complete for now.** The orchestration engine is finished, tested (155 backend + 28 frontend tests, ~87% coverage), and feature-frozen; there is no work in flight. Agents run in a deterministic **mock mode** by default (free, fast, reproducible) with a real-Anthropic mode available; the value here is the *orchestration architecture*, which is real and proven — not a finished app generator. Full detail in [`docs/STATUS.md`](docs/STATUS.md).

Expand Down Expand Up @@ -170,7 +170,7 @@ The design spec and the phased implementation plans (each built test-first and i
- **Proven:** the coordination core, multi-process collision-freedom, approval gates, and live budget downgrade — all under test.
- **Mock by design:** the documented run and tests use mock agents (deterministic, free). Real-Anthropic mode works but isn't required to exercise the architecture; **real token-cost accounting** is the top follow-up (costs are currently simulated, so the downgrade *mechanism* is real while the dollar figures driving it are not).
- **Single-user web bridge:** the live UI targets local single-user use; multi-tenant lifecycle hardening (per-connection dedup, reconnect durability) is future work.
- **Historical docs:** `docs/Roadmap.md`, `docs/CoreDesignDocument.md`, and the dated `docs/Status-*.md` files describe the earlier LangGraph-based design that the engine replaced. They are kept as history; [`docs/STATUS.md`](docs/STATUS.md) is the current one.
- **Historical docs:** `docs/Roadmap.md`, `docs/CoreDesignDocument.md`, and the dated `docs/Status-*.md` files describe an earlier design that this engine replaced. They are kept as history and do not describe what runs today; [`docs/STATUS.md`](docs/STATUS.md) is current.

If the project is picked up again, [`docs/STATUS.md`](docs/STATUS.md) carries the ranked list of what to do first.

Expand Down
Loading