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 }}
Repository navigation
Commit 8d7cd9c
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: CHANGELOG.md
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,6 +7,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
7
7
8
8
## [Unreleased]
9
9
10
+
### Added
11
+
-**`hermes` backend**: `"sdk": "hermes"` engineers a saved capture through the local [`hermes` CLI](https://hermes-agent.nousresearch.com/docs) (`hermes chat --oneshot --format stream-json`), so a run needs no API key in rae — the model, the provider and the authentication are the user's own Hermes configuration. `hermes chat` reads the prompt on stdin, so nothing the model reads is shell-parsed; `hermes_max_turns` overrides the turn cap from the user's Hermes config; runs start with `--ignore-rules` so an `AGENTS.md`/`CLAUDE.md` cannot steer them, and estimate cost from the CLI's token counts, leaving it at 0 for a model with no known price. The backend covers `engineer` only: with `"sdk": "hermes"` the `agent` command stops before browser setup, so capture with another SDK (claude, opencode, copilot or cursor) and engineer that run with hermes; `agent --dry-run` reports the same error. The CLI is found on `PATH` or through `RAE_HERMES_BIN`, and `agent --dry-run` reports it as a check.
Copy file name to clipboardExpand all lines: README.md
+5-1Lines changed: 5 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -108,6 +108,9 @@ Settings live in `~/.reverse-api/config.json` and can be edited via `/settings`
108
108
"opencode_auto_start": true,
109
109
"opencode_base_url": "http://127.0.0.1:4096",
110
110
"opencode_model": "big-pickle",
111
+
"hermes_max_turns": null,
112
+
"hermes_model": null,
113
+
"hermes_provider": null,
111
114
"opencode_npx_package": "opencode-ai@latest",
112
115
"opencode_provider": "opencode",
113
116
"copilot_model": "gpt-5",
@@ -120,7 +123,8 @@ Settings live in `~/.reverse-api/config.json` and can be edited via `/settings`
120
123
```
121
124
122
125
-**Models**: Sonnet 5.5, Opus 5.5 (most capable), Opus 4.6 and Haiku 5.5 (fastest). Sonnet 4.6 stays the default until you choose another; it and Haiku 4.5 are still accepted in config and by `--model`. For OpenCode see [models.dev](https://models.dev).
123
-
-**SDK**: `claude` (default), `opencode`, `cursor`, or `copilot` (GitHub Copilot).
126
+
-**SDK**: `claude` (default), `opencode`, `cursor`, `copilot` (GitHub Copilot), or `hermes`.
127
+
- **Hermes**: engineers a saved capture through the [`hermes` CLI](https://hermes-agent.nousresearch.com/docs) instead of an SDK. It needs Hermes Agent v2026.9.21 or later from the official installer (the PyPI package is older): `curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash` on macOS, Linux and WSL2, `iex (irm https://hermes-agent.nousresearch.com/install.ps1)` in PowerShell on Windows. It needs no API key in rae: the model, the provider and the authentication are your own Hermes configuration. `hermes_model` and `hermes_provider` override which model that configuration runs; leaving them `null` uses whatever Hermes already selects. `hermes_max_turns` overrides the turn cap from your Hermes config. Runs start with `--ignore-rules`, so an `AGENTS.md` or `CLAUDE.md` in the workspace cannot steer the run. Cost is estimated from the token counts the CLI reports, and stays at 0 for a model with no known price. It covers `engineer` only: while `sdk` is `hermes` the `agent` command stops before opening a browser, so capture with `claude`, `opencode`, `copilot` or `cursor`, then switch `sdk` back to `hermes` to engineer that run. `agent --dry-run` reports the same thing.
124
128
-**Claude settings isolation**: Claude sessions don't load your Claude Code settings files, `CLAUDE.md`, hooks, plugins, permission rules or MCP servers, so your personal setup doesn't steer the agent. Organization-managed policy still applies, and Claude Code still reads its own state such as `~/.claude.json` and auto memory. If `~/.claude/settings.json` provides your authentication (`apiKeyHelper`, or Bedrock, Vertex or proxy variables under `env`), set `claude_setting_sources` to the layers to load, e.g. `["user"]` or `["user", "project", "local"]`. Each layer you list is loaded in full, including its hooks, plugins, permission rules and MCP servers.
125
129
-**OpenCode setup**: with `sdk: "opencode"`, RAE reuses an existing server or downloads/starts `opencode-ai@latest` through `npx`; a global OpenCode installation is not required. Fresh configurations default to the free `opencode/big-pickle` model. `/settings` shows a loading list, then offers a searchable **opencode provider / model** list populated from the server's connected, tool-capable catalog and marks free OpenCode options. Before creating a session, RAE validates the saved pair again and suggests currently available free models when configuration is invalid. Compatible older servers are reused with a version warning. Node.js 20+ is required for automatic startup. Password-protected servers use `OPENCODE_SERVER_PASSWORD` and optional `OPENCODE_SERVER_USERNAME`. Override startup with `OPENCODE_BASE_URL`, `RAE_OPENCODE_PACKAGE`, or `RAE_OPENCODE_AUTO_START=0`.
126
130
-**Ollama through OpenCode**: choose provider `ollama` in `/settings`; RAE starts an installed Ollama daemon if needed, lists only installed models with tool calling and 64k+ context, and supplies OpenCode's provider config inline. Models are never downloaded silently. Override with `RAE_OLLAMA_BASE_URL` or `RAE_OLLAMA_AUTO_START=0`.
0 commit comments