* ci: run the architect continuously as the founder lens
Make the architect a continuous overseer (hourly at :59, just before the :29
increment) instead of an every-few-days check-in. Each run it tracks live state
(what merged, what's in flight), keeps the roadmap priorities live, and judges
cohesion across harness/framework/dev-UX plus missing pieces and realignment —
re-ranking internal/docs/PRIORITIES.md to match reality. It only opens a PR when
the ranking actually changes (otherwise it just posts an assessment and closes
its issue), to avoid churn.
* thesis: lead the North Star with the mission, grounded in the canon
Instill the years of context the loop was missing: the vision lives in the
corpus (blog, README, website), not a single doc. Lead THESIS.md with an
explicit Mission — "what problem we solve" (make building an agent as easy as
building a service, on one runtime, because an agent is a distributed system),
distilled from the corpus — and name the blog/README/website as the canon the
North Star is a distillation of and must stay faithful to. Wire the architect to
judge every priority against the mission and re-derive alignment from the canon,
flagging drift in either direction (work vs mission, or thesis vs the blog).
---------
Co-authored-by: Claude <noreply@anthropic.com>
The architect now prioritizes the roadmap + an internal scan into a single
ranked, issue-linked queue in internal/docs/PRIORITIES.md (re-ranked each run),
and the hourly increment loop works the top open item from that queue instead
of independently guessing each hour — falling back to its own judgment only
when the queue is empty. So work is roadmap-driven by default and the human can
redirect by reordering the file or its issues.
- New internal/docs/PRIORITIES.md (seeded from the roadmap + open issues).
- architecture-review.yml: architect owns/re-ranks PRIORITIES.md and keeps each
top item backed by a scoped issue.
- continuous-improvement.yml: pick the top open queue item; close both the
priority issue and the run tracker.
- CONTINUOUS_IMPROVEMENT.md: document the architect → queue → increment pipeline.
Co-authored-by: Claude <noreply@anthropic.com>
A post on how the framework is increasingly built by an autonomous loop of
two AI agents (Codex implementing scoped increments, Claude Code
orchestrating, the human setting direction): the dispatch→build→auto-merge
mechanism, the three altitudes (architect/increment/DevRel), the failure
modes we hit wiring it up, and the concrete increments it produces.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
The hourly loop ships increments but nothing watches the whole. Add two
periodic high-altitude passes, same dispatch mechanism (fresh issue → @codex):
- devrel-review.yml (daily): audits README, website, docs, blog for coherence
with the North Star, README crispness, and blog-worthy material. Safe
alignment/crispness fixes auto-merge; brand/positioning copy and blog drafts
are surfaced in a report for the human, never auto-merged.
- architecture-review.yml (every ~3 days): reviews the framework/harness against
the thesis and files scoped follow-up issues that feed the increment loop. It
does not make breaking/architectural changes itself.
Documented both in CONTINUOUS_IMPROVEMENT.md (Overseer passes).
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
The section only mentioned micro run (services) and micro deploy. Update it
to the current lifecycle DX: micro new scaffolds a service or agent (every
endpoint an MCP tool), micro run starts everything with hot reload + gateway
+ console, and micro chat talks to agents and services. Drops micro deploy.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
* ci: self-merge Codex PRs via native auto-merge; retire the sweep
With branch protection + "Allow auto-merge" now enabled on master, Codex
enables GitHub auto-merge on its own PR (gh pr merge --squash --auto) right
after opening it, so the PR lands the moment the required CI checks pass —
no polling sweep, and the green-CI gate is enforced by GitHub instead of by
gh pr checks in a cron. Removes auto-merge-codex.yml and updates the dispatch
and AGENTS.md accordingly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* docs: document the durable loop mechanics (stub→gh, branch, auto-merge)
Capture the hard-won wiring of the autonomous loop so it isn't re-derived:
fresh issue per increment, user-PAT dispatch (Codex ignores the bot), Codex
opening the PR via gh (make_pr is a no-op stub), unique codex/ branch + label,
and native auto-merge gated by branch protection with 0 approvals. Adds a
"do-not-break" list (don't re-add approvals, don't reuse one tracker issue,
don't use make_pr, don't re-implement during the summary→PR lag).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
* website: rename section to "Features"; trim subtitle
Rename the feature-grid heading from "The Runtime Around the Agent" to
"Features", and drop "once they leave the demo." from the subtitle.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
---------
Co-authored-by: Claude <noreply@anthropic.com>
Add a 'Where we fit' section: 'harness' has two layers — the intra-agent
harness (single-model runtime: prompts, tools, context, sandbox, the Ralph
loop) that LangChain/LangGraph/deepagents/Claude Code own and we do NOT
compete with, and the operational harness (the distributed substrate agents
operate inside: services-as-tools, discovery, durable runs, observability,
interop, the services->agents->workflows lifecycle) which is our focus. They
stack and interoperate via MCP/A2A; we make those agents better neighbours,
not obsolete.
Co-authored-by: Claude <noreply@anthropic.com>
Grid items defaulted to min-width:auto, so the wide <pre> blocks (install
command, the 'micro run' sample) forced their row past the viewport —
clipped by overflow-x:hidden, so no scroll but not fitting either. Let
grid items shrink (.two-col > * { min-width:0 }) and wrap the code blocks
on mobile (white-space:pre-wrap; overflow-wrap:anywhere) so every section
fits the screen with no overflow or scroll.
Co-authored-by: Claude <noreply@anthropic.com>
Replace the docs header 'Menu' button with a ☰ burger icon and move it to the
left next to the wordmark (where the logo used to be), grouped in a .nav-left
container. Keeps id=menuToggle so the existing sidebar-toggle JS still works;
desktop is unchanged (toggle hidden).
Co-authored-by: Claude <noreply@anthropic.com>
Remove the logo image from the nav-brand in the marketing nav include and the
docs and blog layouts; the brand is now just the 'Go Micro' wordmark.
Co-authored-by: Claude <noreply@anthropic.com>
Add internal/docs/THESIS.md — the vision the autonomous loop steers by: a
holistic agent harness AND service framework encapsulating the lifecycle of
services -> agents -> workflows (workloads come after agents; the value is in
composing it into systems that do real work, on schedules and in loops).
Wire it in as the alignment criterion: the continuous-improvement charter and
the Codex dispatch prompt now require every increment to advance the North Star,
so improvements compound toward the thesis instead of drifting locally.
Co-authored-by: Claude <noreply@anthropic.com>
* loop: establish the continuous-improvement charter + scheduled backbone
Define the autonomous improvement loop (internal/docs/CONTINUOUS_IMPROVEMENT.md):
full autonomy with correctness (build/test/lint) as the only gate, work sourced
from roadmap + issues + an improvement radar + dogfooding, Claude Code driving
and Codex executing scoped tasks, with brand/positioning and breaking API kept
with the human.
Add a durable scheduled GitHub Action (.github/workflows/continuous-improvement.yml)
as the session-independent backbone — a safe no-op until an ANTHROPIC_API_KEY
secret is added.
* docs: mark harness Resilience as shipped
Resilience (per-call timeout + context propagation + opt-in retry/backoff)
landed in #3017/#3021; update the agent-harness status table from
'In progress' to 'Shipped'.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Define the autonomous improvement loop (internal/docs/CONTINUOUS_IMPROVEMENT.md):
full autonomy with correctness (build/test/lint) as the only gate, work sourced
from roadmap + issues + an improvement radar + dogfooding, Claude Code driving
and Codex executing scoped tasks, with brand/positioning and breaking API kept
with the human.
Add a durable scheduled GitHub Action (.github/workflows/continuous-improvement.yml)
as the session-independent backbone — a safe no-op until an ANTHROPIC_API_KEY
secret is added.
Co-authored-by: Claude <noreply@anthropic.com>
- h1: 'An Agent Harness and Service Framework' (drop 'in Go')
- tagline: 'Build agents, services, and workflows on one runtime'
- move the hero image into the hero block (between tagline and the install
line), capped at 800px to fit the hero column, and remove the separate
full-width image section
Co-authored-by: Claude <noreply@anthropic.com>
- Regenerate the hero image (text-free, via the framework's own Atlas Cloud
image model) — an agent orchestrating service nodes. The old one had baked-in
'AI native microservices framework' text that contradicts the positioning;
text-free so copy changes can't invalidate it again.
- h1 -> 'An Agent Harness and Service Framework in Go' (both, not harness-only).
- Tagline reframed around agents, services, and flows on one runtime.
- Drop the 'moved from a service framework to an agent harness' line — it's
additive (both in one), not a pivot away from services.
Co-authored-by: Claude <noreply@anthropic.com>
- Add the canonical concept doc 'The Agent Harness' (docs/guides/agent-harness.md)
+ nav entry: what the harness is, each piece mapped to a feature, honest
about shipped vs in-progress.
- Add blog post /blog/30 'Go Micro is an Agent Harness' (the public articulation;
precise about what ships today vs the Now/Next roadmap).
- Align the ROADMAP.md opening line to the agent-harness framing.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Follow-up to #3006:
- provider-conformance: build each harness to a temp binary and run that
instead of 'go run'. 'go run' launches the harness as a child it doesn't
kill on context cancellation, so a timed-out harness (which starts local
services) could be orphaned and outlive the run. Running the built binary
makes the per-run timeout actually terminate the work.
- contract test: skip under -short, and use 'go build ./...' instead of
'go test ./...' (the contract is that the generated service builds). This
keeps the default unit-test suite from shelling out to the toolchain and
the network on every run.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Add a blog post for the OpenAI Codex for Open Source grant, list it on
the blog index, and repoint the OpenAI sponsor logo (README + landing) to
the post — matching how the Anthropic (/blog/3) and Atlas Cloud (/blog/8)
sponsor logos link to their posts.
Co-authored-by: Claude <noreply@anthropic.com>
Go Micro received an OpenAI Codex for Open Source grant. Add the OpenAI
logo to the README and landing-page sponsors, alongside Anthropic and
Atlas Cloud.
Co-authored-by: Claude <noreply@anthropic.com>
Adds the agentic 'loop' to flows: flow.Loop(body, opts...) is a StepFunc
that runs a body step repeatedly, carrying State across passes, until a
stop condition fires or a hard iteration cap is reached.
- Stop modes: flow.Until (code-defined predicate) and flow.UntilLLM (the
model judges the goal met after each pass — the supervised 'Ralph'
loop). Either firing stops the loop.
- flow.LoopMax is the guardrail: the body never runs more than n times, so
the loop always terminates and can't run up an unbounded bill. Hitting
the cap returns the latest state rather than erroring.
- flow.OnIteration reports per-pass progress.
- Composes as a normal flow step (checkpointed by the step engine).
- Exposed at the top level as micro.FlowLoop / FlowUntil / FlowUntilLLM /
FlowLoopMax / FlowOnIteration, symmetric with the other Flow* helpers.
Includes tests, an offline runnable example (examples/flow-loop), an
'Agent Loops' guide, and a CHANGELOG entry.
Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL
Co-authored-by: Claude <noreply@anthropic.com>
Extract the nav and footer link lists into _includes/nav-links.html and
_includes/footer-links.html, and the full marketing nav/footer into
_includes/marketing-nav.html and _includes/marketing-footer.html.
- index.html and support.html now pull their nav/footer from the shared
marketing includes (and gain Liquid front matter so includes resolve).
- The docs and blog layouts pull the same link lists, so a nav/footer
link lives in exactly one place site-wide. This also adds the missing
Support link to the blog nav and fixes the blog footer's Support link
(it still pointed at the question template).
- Active nav state is driven by a per-page nav_active flag.
Verified with a local jekyll build: landing, support, docs, and blog
pages all render the shared nav/footer correctly.
Co-authored-by: Claude <noreply@anthropic.com>
* website: add Support to top nav (landing + docs layout)
Link /docs/support.html from the nav bar on the landing page and the
shared docs layout, and point the docs-layout footer Support link there
too (was the question issue template).
* website: add a dedicated marketing /support page
New top-level /support.html styled like the landing site (hero, tier
cards, community links, CTAs) — separate from the docs reference at
/docs/support.html. Repoint the site nav, footer, landing 'Commercial
support' button, and the FUNDING button to it.
* website: serve the support page at a clean /support URL
Add 'permalink: /support' to support.html (same mechanism the blog uses)
and point all nav/footer/CTA/FUNDING links at /support instead of
/support.html.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Drop the 'Every service is an MCP tool; every agent speaks A2A' sentence
and use 'workflows' (clearer than 'flows') in the one-liner.
Co-authored-by: Claude <noreply@anthropic.com>
Codex