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
**Athena** is a production-ready general AI agent built to *do*, not just *think*. It bridges insight with execution, helping you move from idea to results effortlessly.
14
+
**Athena** is a production-ready general AI agent built to _do_, not just _think_. It bridges insight with execution, helping you move from idea to results effortlessly.
15
15
16
16
Some examples of what Athena can do:
17
17
@@ -47,23 +47,27 @@ With all the tools it has, Athena is capable of:
> For a complete list of plugins and detailed configuration options, please refer to the [Configuration Guide](docs/configuration.md). See [Cerebrum](docs/configuration.md#cerebrum) section for best practices on selecting the right model for your use case.
100
104
101
105
6. Launch Athena:
106
+
102
107
```bash
103
108
pnpm start
104
109
```
@@ -117,25 +122,30 @@ Trust us: the AI will probably do a better job explaining it than we ever could.
117
122
118
123
## 🗓️ Roadmap
119
124
120
-
Our mission is to realize **human-level intelligence**, or *AGI*, by evolving Athena into a truly autonomous and capable agent. Here's a more detailed roadmap of what we're working on:
125
+
Our mission is to realize **human-level intelligence**, or _AGI_, by evolving Athena into a truly autonomous and capable agent. Here's a more detailed roadmap of what we're working on:
121
126
122
127
-[ ]**Autonomous Code Writing**
128
+
123
129
- Enable Athena to iteratively write and improve its own plugins
124
130
125
131
-[ ]**Robust Browser Automation**
132
+
126
133
- Improve reliability and fault tolerance in headless and headful modes
127
134
- Add advanced DOM element parsing and interaction strategies
128
135
129
136
-[ ]**Context Management Improvements**
137
+
130
138
- Adjust prompt context windows for different LLMs
131
139
- Implement context summarization for out-of-window context
132
140
133
141
-[ ]**Long-Term Memory with RAG**
142
+
134
143
- Set up vector database integration for persistent knowledge
135
144
- Enable memory recall across sessions and tasks
136
145
- Support user-specific long-term context embedding and retrieval
137
146
138
147
-[ ]**Image and Video Model Expansion**
148
+
139
149
- Integrate support for more image and video generation models
140
150
- Enable multimodal workflows that combine text, image, and video reasoning
141
151
@@ -148,7 +158,7 @@ Our mission is to realize **human-level intelligence**, or *AGI*, by evolving At
148
158
149
159
We welcome contributions from everyone — whether you're fixing a typo, suggesting a feature, or building a whole new plugin!
150
160
151
-
Athena is a community-driven project, and we believe in building great tools *together*. Here's how you can help:
161
+
Athena is a community-driven project, and we believe in building great tools _together_. Here's how you can help:
152
162
153
163
### 💡 Got an Idea?
154
164
@@ -166,6 +176,7 @@ Open a [GitHub Issue](https://github.com/Athena-AI-Lab/athena-core/issues) and l
166
176
### 🧪 Suggest Tests or Improvements
167
177
168
178
Not into code? You can still help by:
179
+
169
180
- Testing features and reporting issues
170
181
- Improving documentation
171
182
- Sharing Athena with others and providing feedback
Copy file name to clipboardExpand all lines: docs/configuration.md
+73-73Lines changed: 73 additions & 73 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -29,8 +29,8 @@ Plugins are the core components of Athena. Each plugin has its own configuration
29
29
The `browser` plugin allows Athena to control a web browser via Playwright.
30
30
31
31
```yaml
32
-
browser:
33
-
headless: true
32
+
browser:
33
+
headless: true
34
34
```
35
35
36
36
- `headless`: Whether to run the browser in headless mode. If set to `true`, the browser will not be visible.
@@ -42,43 +42,43 @@ The `cerebrum` plugin is the main plugin for Athena. It handles event receiving,
42
42
Here is a configuration example for the cerebrum plugin using GPT-4o:
43
43
44
44
```yaml
45
-
cerebrum:
46
-
base_url: https://api.openai.com/v1
47
-
api_key: sk-proj-your-openai-api-key
48
-
model: gpt-4o
49
-
temperature: 0.5
50
-
image_supported: true
51
-
max_prompts: 50
52
-
max_event_strlen: 65536
53
-
max_tokens: 16384
45
+
cerebrum:
46
+
base_url: https://api.openai.com/v1
47
+
api_key: sk-proj-your-openai-api-key
48
+
model: gpt-4o
49
+
temperature: 0.5
50
+
image_supported: true
51
+
max_prompts: 50
52
+
max_event_strlen: 65536
53
+
max_tokens: 16384
54
54
```
55
55
56
56
However, Athena performs best with DeepSeek V3 (not 0324). The web app version of Athena uses DeepSeek V3 as its cerebrum model. Here is an example configuration for DeepSeek V3:
57
57
58
58
```yaml
59
-
cerebrum:
60
-
base_url: https://openrouter.ai/api/v1
61
-
api_key: sk-your-openrouter-api-key
62
-
model: deepseek/deepseek-chat
63
-
temperature: 0.5
64
-
image_supported: false
65
-
max_prompts: 50
66
-
max_event_strlen: 65536
67
-
max_tokens: 16384
59
+
cerebrum:
60
+
base_url: https://openrouter.ai/api/v1
61
+
api_key: sk-your-openrouter-api-key
62
+
model: deepseek/deepseek-chat
63
+
temperature: 0.5
64
+
image_supported: false
65
+
max_prompts: 50
66
+
max_event_strlen: 65536
67
+
max_tokens: 16384
68
68
```
69
69
70
70
Although more expensive, Athena can perform even better with Claude 3.7 Sonnet. Here is an example configuration:
71
71
72
72
```yaml
73
-
cerebrum:
74
-
base_url: https://api.anthropic.com/v1
75
-
api_key: sk-ant-api03-your-anthropic-api-key
76
-
model: claude-3-7-sonnet-latest
77
-
temperature: 0.5
78
-
image_supported: false
79
-
max_prompts: 50
80
-
max_event_strlen: 65536
81
-
max_tokens: 16384
73
+
cerebrum:
74
+
base_url: https://api.anthropic.com/v1
75
+
api_key: sk-ant-api03-your-anthropic-api-key
76
+
model: claude-3-7-sonnet-latest
77
+
temperature: 0.5
78
+
image_supported: false
79
+
max_prompts: 50
80
+
max_event_strlen: 65536
81
+
max_tokens: 16384
82
82
```
83
83
84
84
- `base_url`: The base URL of the API endpoint.
@@ -95,29 +95,29 @@ Although more expensive, Athena can perform even better with Claude 3.7 Sonnet.
95
95
Enable `cli-ui` to interact with Athena via the command line. If not needed, you can remove it from the `plugins` section.
96
96
97
97
```yaml
98
-
cli-ui:
98
+
cli-ui:
99
99
```
100
100
101
101
### Clock
102
102
103
103
The `clock` plugin provides time awareness and scheduling. When enabled, Athena can get the current date and time, and manage timers and alarms.
104
104
105
105
```yaml
106
-
clock:
106
+
clock:
107
107
```
108
108
109
109
### Discord
110
110
111
111
Enable `discord` for Athena to send and receive messages from Discord.
112
112
113
113
```yaml
114
-
discord:
115
-
bot_token: your-discord-bot-token
116
-
allowed_channel_ids:
117
-
- "1234567890"
118
-
- "9876543210"
119
-
admin_channel_ids: []
120
-
log_channel_ids: []
114
+
discord:
115
+
bot_token: your-discord-bot-token
116
+
allowed_channel_ids:
117
+
- "1234567890"
118
+
- "9876543210"
119
+
admin_channel_ids: []
120
+
log_channel_ids: []
121
121
```
122
122
123
123
- `bot_token`: The Discord bot token.
@@ -130,21 +130,21 @@ Enable `discord` for Athena to send and receive messages from Discord.
130
130
Enable `file-system` to allow Athena to access your local file system. Athena will be able to read and write files.
131
131
132
132
```yaml
133
-
file-system:
133
+
file-system:
134
134
```
135
135
136
136
### HTTP
137
137
138
138
Enable `http` for Athena to send HTTP requests, search the web via Jina Search or Exa Search, and download files from the Internet.
139
139
140
140
```yaml
141
-
http:
142
-
jina: # Optional Jina config
143
-
base_url: https://s.jina.ai
144
-
api_key: your-jina-api-key
145
-
exa: # Optional Exa config
146
-
base_url: https://api.exa.ai # Optional, defaults to this
147
-
api_key: your-exa-api-key # Required if using Exa
141
+
http:
142
+
jina: # Optional Jina config
143
+
base_url: https://s.jina.ai
144
+
api_key: your-jina-api-key
145
+
exa: # Optional Exa config
146
+
base_url: https://api.exa.ai # Optional, defaults to this
147
+
api_key: your-exa-api-key # Required if using Exa
148
148
```
149
149
150
150
- `jina`: Configuration for [Jina Search](https://jina.ai/). (Optional)
@@ -159,24 +159,24 @@ Enable `http` for Athena to send HTTP requests, search the web via Jina Search o
159
159
Enable `llm` for Athena to chat with other language models and generate images.
160
160
161
161
Since only a single OpenAI endpoint can be configured currently, it's recommended to use a service like LiteLLM proxy to route requests to different language models. OpenRouter is another option, though it doesn't support image generation.
162
-
162
+
163
163
```yaml
164
-
llm:
165
-
base_url: https://openrouter.ai/api/v1
166
-
api_key: sk-or-v1-your-openrouter-api-key
167
-
models:
168
-
chat:
169
-
- name: openai/gpt-4o
170
-
desc: GPT-4o is good at general purpose tasks. Supports image input. Whenever you receive an image and need to understand it, pass it to this model using the image arg.
171
-
- name: openai/o3-mini
172
-
desc: O3 Mini is good at deep thinking and planning. Whenever you need to plan something complicated or solve complex math problems, use this model.
173
-
- name: anthropic/claude-3.7-sonnet
174
-
desc: Claude 3.7 Sonnet is good at writing code. Whenever you need to write code, use this model.
175
-
- name: perplexity/sonar
176
-
desc: Perplexity can access the Internet. Whenever you need to search the Internet, use this model.
177
-
image:
178
-
- name: openai/dall-e-3 # OpenRouter doesn't support image generation
179
-
desc: DALL-E 3 is good at generating images. Whenever you are requested to generate images, use this model.
164
+
llm:
165
+
base_url: https://openrouter.ai/api/v1
166
+
api_key: sk-or-v1-your-openrouter-api-key
167
+
models:
168
+
chat:
169
+
- name: openai/gpt-4o
170
+
desc: GPT-4o is good at general purpose tasks. Supports image input. Whenever you receive an image and need to understand it, pass it to this model using the image arg.
171
+
- name: openai/o3-mini
172
+
desc: O3 Mini is good at deep thinking and planning. Whenever you need to plan something complicated or solve complex math problems, use this model.
173
+
- name: anthropic/claude-3.7-sonnet
174
+
desc: Claude 3.7 Sonnet is good at writing code. Whenever you need to write code, use this model.
175
+
- name: perplexity/sonar
176
+
desc: Perplexity can access the Internet. Whenever you need to search the Internet, use this model.
177
+
image:
178
+
- name: openai/dall-e-3 # OpenRouter doesn't support image generation
179
+
desc: DALL-E 3 is good at generating images. Whenever you are requested to generate images, use this model.
180
180
```
181
181
182
182
- `base_url`: The base URL of the API endpoint.
@@ -194,37 +194,37 @@ Since only a single OpenAI endpoint can be configured currently, it's recommende
194
194
Enable `python` for Athena to run inline Python code or Python scripts. This also enables Athena to install pip packages.
195
195
196
196
```yaml
197
-
python:
197
+
python:
198
198
```
199
199
200
200
### Shell
201
201
202
202
Enable `shell` for Athena to run shell commands.
203
203
204
204
```yaml
205
-
shell:
205
+
shell:
206
206
```
207
207
208
208
### Short-Term Memory
209
209
210
210
Enable `short-term-memory` for Athena to manage a basic task list.
211
211
212
212
```yaml
213
-
short-term-memory:
213
+
short-term-memory:
214
214
```
215
215
216
216
### Telegram
217
217
218
218
Enable `telegram` for Athena to send and receive messages from Telegram.
0 commit comments