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
|[Agent Framework patterns](docs/agent_framework_patterns.md)| Examples for the investment domain. | Explore features one at a time. |
25
+
|[Real-time terminal dashboard](docs/chart_cli.md)| Live watchlist and charts driven by an Agent Framework workflow, with `/ask`, `/model`, and `/help` commands. | Watch signals update in a terminal. |
25
26
|[Framework comparison](docs/autogen_agent_sk.md)| Short comparison of the three frameworks. | - |
26
27
27
28
The [Agent Framework patterns](docs/agent_framework_patterns.md) are the only pattern showcase in this repository. The 30 examples show Microsoft Agent Framework features for investment research. Semantic Kernel and AutoGen do not have separate pattern libraries here.
@@ -57,6 +58,27 @@ Use this command only when comparing the plugin-based agent variant. It reuses t
57
58
uv run python -m semantic_kernel.main
58
59
```
59
60
61
+
## Real-time terminal dashboard
62
+
63
+
[chart-cli](docs/chart_cli.md) renders a live watchlist, price chart, and Agent Framework workflow output in the terminal. Press `/` for the command prompt: `/ask` answers questions about the symbols on screen, `/model` switches the chat backend, `/help` lists everything. The screenshot below is a real capture of the running dashboard; `AGENT:RULES` means the workflow fell back to its transparent rule-based path because no Foundry credentials were available.
64
+
65
+
<imgsrc="docs/chart-cli-dashboard.png"alt="chart-cli terminal dashboard with a watchlist, price chart, details, workflow signals, agent call, and market and risk notes"width="900">
66
+
67
+
Run this from PowerShell:
68
+
69
+
```powershell
70
+
cd chart-cli
71
+
pnpm install
72
+
.\scripts\test-cli.ps1
73
+
```
74
+
75
+
The script verifies the Node UI and Python Agent Framework protocol, then opens
76
+
the interactive dashboard in the same terminal. It starts the workflow process
77
+
used by the dashboard; do not start a separate Python backend. Use
78
+
`.\scripts\test-cli.ps1 -CheckOnly` for verification without opening the UI.
79
+
80
+
See the [terminal dashboard guide](docs/chart_cli.md) for the panels, keys, commands, ticker editing, and provider setup.
81
+
60
82
## Sample research output
61
83
62
84
The following Agent Framework sample uses `MSFT` from 2020-01-01 through 2026-07-01 with a simulated $10,000 starting balance. It is historical research only; a later run can generate a different strategy and result.
@@ -102,6 +124,7 @@ See the full [backtest workbook](output/agent_framework/backtest_results.xlsx),
102
124
|[semantic_kernel](semantic_kernel)| The Semantic Kernel version of the research workflow. |
103
125
|[autogen](autogen)| The AutoGen reference version, with its own Poetry environment. |
104
126
|[agent_framework_patterns](agent_framework_patterns)| Thirty small Agent Framework examples for investment research. |
127
+
|[chart-cli](chart-cli)| Real-time terminal dashboard with a companion Agent Framework workflow. |
105
128
|[tests](tests)| Offline tests for Agent Framework patterns and the REPL contracts. |
106
129
|[output](output)| Saved charts, metrics, and example pattern responses. |
107
130
|[docs](docs)| Guides for each implementation and framework comparison. |
0 commit comments