Skip to content

Commit 7e2b8cd

Browse files
committed
Merge branch 'docs/independent-runtime' into chore/merge-all-feature-branches
2 parents f284097 + e900b39 commit 7e2b8cd

2 files changed

Lines changed: 15 additions & 8 deletions

File tree

‎AGENTS.md‎

Lines changed: 6 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -161,10 +161,12 @@ make ci # Full CI suite
161161
| Main test file | `provider/client_test.go` (httptest servers, provider detection) |
162162
| Linter config | `.golangci.yml` (govet, ineffassign, misspell — minimal) |
163163

164-
This is an independent repository consumed by Reflect. In the local
165-
`graycode-eco` parent workspace it is checked out beside `reflect` as `../relay`
166-
and connected through the parent `go.work`; publish changes here, then update
167-
Reflect's module pin through a separate PR.
164+
Relay is an independent open-source GrayCodeAI project that any application can
165+
consume. Reflect is one host, with its own repository, build, version, and release.
166+
Relay does not depend on Reflect. Optional coordinated development uses a
167+
gitignored module overlay in the host; no parent `go.work` or sibling checkout
168+
is required. Publish Relay changes independently, then consumers update their
169+
module pins through their own release processes.
168170

169171
## Cloudflare
170172

‎README.md‎

Lines changed: 9 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -30,13 +30,16 @@
3030

3131
## What is relay
3232

33-
relay is the LLM provider runtime that powers the [reflect](https://github.com/GrayCodeAI/reflect) coding agent. It handles everything between your application and LLM APIs — authentication, model resolution, streaming, retries, rate limiting, and caching.
33+
Relay is an independent open-source LLM provider runtime from GrayCodeAI, built
34+
for any application that needs model access. It handles authentication, model
35+
resolution, streaming, retries, rate limiting, and caching.
3436

3537
When your app calls a model, relay figures out which provider to use, how to talk to it, and how to stream the response back. Switch from Anthropic to Ollama? relay handles the translation. API returns 529? relay retries with backoff. Response hits `max_tokens`? relay continues automatically.
3638

3739
**Your app never talks to an LLM API directly. relay does.**
3840

39-
Reflect is the product face: it owns UX, agent orchestration, tools, permissions,
41+
The [Reflect](https://github.com/GrayCodeAI/reflect) coding agent is one consumer:
42+
it owns UX, agent orchestration, tools, permissions,
4043
sessions, and product semantics. Relay is the provider engine: it owns
4144
credentials, catalog and route resolution, provider transports, normalized
4245
streams, retry/fallback, usage, and provider telemetry. Reflect integrates through
@@ -45,7 +48,9 @@ provider packages.
4548

4649
## Ecosystem Boundaries
4750

48-
relay is a Reflect support engine. Keep the dependency edge one-way.
51+
Relay and Reflect are independently usable, versioned, and released projects.
52+
Relay has no dependency on Reflect. Any host application can integrate through
53+
Relay's public API; agent behavior and product UX belong to that host.
4954

5055
Hosts may import exactly four packages:
5156

@@ -361,7 +366,7 @@ tool-call count, and deployment-routing state remain queryable.
361366

362367
## Ecosystem
363368

364-
relay is part of the graycode-eco:
369+
GrayCodeAI maintains these independent open-source projects:
365370

366371
| Component | Repository | Purpose |
367372
|---|---|---|

0 commit comments

Comments
 (0)