microsoft-agent-framework

Name: microsoft-agent-framework
Author: managedcode

461stars35forks

How to install microsoft-agent-framework?

managedcode/dotnet-skills/microsoft-agent-framework

$npx -y skills add managedcode/dotnet-skills --skill microsoft-agent-framework

Installs into the current project.

Summary

Build .NET AI agents and multi-agent workflows with Microsoft Agent Framework using the right agent type, threads, tools, workflows, hosting protocols, and enterprise guardrails. USE FOR: building or reviewing .NET code that uses Microsoft.Agents.*, Microsoft.Extensions.AI, AIAge

Files · 1

View on GitHub

SKILL.md

1	# Microsoft Agent Framework
2
3	## Trigger On
4
5	- building or reviewing `.NET` code that uses `Microsoft.Agents.*`, `Microsoft.Extensions.AI`, `AIAgent`, `AgentThread`, `AgentSession`, or Agent Framework hosting packages
6	- choosing between `ChatClientAgent`, Responses agents, hosted agents, custom agents, Anthropic agents, workflows, or durable agents
7	- authoring preview-era `Microsoft.Agents.AI.Workflows.Declarative*` packages or wrapping a workflow with `workflow.AsAIAgent()`
8	- adding tools, MCP, A2A, OpenAI-compatible hosting, AG-UI, DevUI, background responses, or OpenTelemetry
9	- migrating from Semantic Kernel agent APIs or aligning AutoGen-style multi-agent patterns to Agent Framework
10	- using Anthropic Claude models (haiku, sonnet, opus) via `AnthropicClient` or through Azure Foundry with `AnthropicFoundryClient`
11
12	## Workflow
13
14	1. Decide whether the problem should stay deterministic. If plain code or a typed workflow without LLM autonomy is enough, do that instead of adding an agent.
15	2. Choose the execution shape first: single `AIAgent`, explicit programmatic `Workflow`, workflow-as-agent wrapper, declarative workflow when YAML portability is explicitly required, Azure Functions durable agent, ASP.NET Core hosted agent, AG-UI remote UI, or DevUI local debugging.
16	3. Choose the agent type and provider intentionally. Prefer the simplest agent that satisfies the threading, tooling, and hosting requirements.
17	4. Keep agents stateless and keep conversation or long-lived state in provider-owned session objects. Most persistence guidance still centers on `AgentThread`, while newer middleware and background-response examples may surface `AgentSession`. Treat both as opaque provider-specific state.
18	5. Add only the tools and middleware that the scenario needs. Narrow the tool surface, require approval for side effects, and treat MCP, A2A, and third-party services as trust boundaries.
19	6. For workflows, model executors, edges, typed `RequestPort` boundaries, checkpoints, shared state, and human-in-the-loop explicitly rather than hiding control flow in prompts.
20	7. Prefer Responses-based protocols for new remote/OpenAI-compatible integrations unless you specifically need Chat Completions compatibility.
21	8. Use durable agents only when you truly need Azure Functions serverless hosting, durable thread storage, or deterministic long-running orchestrations.
22	9. Verify preview status, package maturity, docs recency, and provider-specific limitations before locking a production architecture.
23
24	## Current Upstream Notes
25
26	- The July 2026 overview now describes one Agent Framework across .NET, Python, and Go. This catalog skill remains intentionally .NET-scoped; do not infer API or feature parity from cross-language overview wording.
27	- The refreshed AG-UI security guidance keeps the browser outside the trust boundary: put a trusted frontend/server mediator in front of the AG-UI server, validate client-supplied messages, state, tools, and forwarded properties, and filter sensitive tool or agent output before streaming it back.
28	- Middleware, function-tool, migration, support, troubleshooting, upgrade, durable-agent, observability, and AG-UI pages all changed in the same review window. Check the exact current .NET page before relying on a Python example or an older preview signature.
29
30	## Architecture
31
32	```mermaid
33	flowchart LR
34	A["Task"] --> B{"Deterministic code is enough?"}
35	B -->\|Yes\| C["Write normal .NET code or a plain workflow"]
36	B -->\|No\| D{"One dynamic decision-maker is enough?"}
37	D -->\|Yes\| E["Use an `AIAgent` / `ChatClientAgent`"]
38	D -->\|No\| F["Use a typed `Workflow`"]
39	F --> G{"Needs durable Azure hosting or week-long execution?"}
40	G -->\|Yes\| H["Use durable agents on Azure Functions"]
41	G -->\|No\| I["Use in-process workflows"]
42	E --> J{"Need a remote protocol or UI?"}
43	F --> J
44	J -->\|OpenAI-compatible HTTP\| K["ASP.NET Core Hosting.OpenAI"]
45	J -->\|Agent-to-agent protocol\| L["A2A hosting"]
46	J -->\|Web UI protocol\| M["AG-UI"]
47	J -->\|Local debug shell\| N["DevUI (dev only)"]
48	```
49
50	## Core Knowledge
51
52	- `AIAgent` is the common runtime abstraction. It should stay mostly stateless.
53	- `AgentThread` still anchors most persisted conversation guidance,

People who liked this also viewed

6 picks

Type

microsoft-agent-framework

461stars35forks

View on GitHub

How to install microsoft-agent-framework?

managedcode/dotnet-skills/microsoft-agent-framework

$npx -y skills add managedcode/dotnet-skills --skill microsoft-agent-framework

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Microsoft Agent Framework
2
3	## Trigger On
4
5	- building or reviewing `.NET` code that uses `Microsoft.Agents.*`, `Microsoft.Extensions.AI`, `AIAgent`, `AgentThread`, `AgentSession`, or Agent Framework hosting packages
6	- choosing between `ChatClientAgent`, Responses agents, hosted agents, custom agents, Anthropic agents, workflows, or durable agents
7	- authoring preview-era `Microsoft.Agents.AI.Workflows.Declarative*` packages or wrapping a workflow with `workflow.AsAIAgent()`
8	- adding tools, MCP, A2A, OpenAI-compatible hosting, AG-UI, DevUI, background responses, or OpenTelemetry
9	- migrating from Semantic Kernel agent APIs or aligning AutoGen-style multi-agent patterns to Agent Framework
10	- using Anthropic Claude models (haiku, sonnet, opus) via `AnthropicClient` or through Azure Foundry with `AnthropicFoundryClient`
11
12	## Workflow
13
14	1. Decide whether the problem should stay deterministic. If plain code or a typed workflow without LLM autonomy is enough, do that instead of adding an agent.
15	2. Choose the execution shape first: single `AIAgent`, explicit programmatic `Workflow`, workflow-as-agent wrapper, declarative workflow when YAML portability is explicitly required, Azure Functions durable agent, ASP.NET Core hosted agent, AG-UI remote UI, or DevUI local debugging.
16	3. Choose the agent type and provider intentionally. Prefer the simplest agent that satisfies the threading, tooling, and hosting requirements.
17	4. Keep agents stateless and keep conversation or long-lived state in provider-owned session objects. Most persistence guidance still centers on `AgentThread`, while newer middleware and background-response examples may surface `AgentSession`. Treat both as opaque provider-specific state.
18	5. Add only the tools and middleware that the scenario needs. Narrow the tool surface, require approval for side effects, and treat MCP, A2A, and third-party services as trust boundaries.
19	6. For workflows, model executors, edges, typed `RequestPort` boundaries, checkpoints, shared state, and human-in-the-loop explicitly rather than hiding control flow in prompts.
20	7. Prefer Responses-based protocols for new remote/OpenAI-compatible integrations unless you specifically need Chat Completions compatibility.
21	8. Use durable agents only when you truly need Azure Functions serverless hosting, durable thread storage, or deterministic long-running orchestrations.
22	9. Verify preview status, package maturity, docs recency, and provider-specific limitations before locking a production architecture.
23
24	## Current Upstream Notes
25
26	- The July 2026 overview now describes one Agent Framework across .NET, Python, and Go. This catalog skill remains intentionally .NET-scoped; do not infer API or feature parity from cross-language overview wording.
27	- The refreshed AG-UI security guidance keeps the browser outside the trust boundary: put a trusted frontend/server mediator in front of the AG-UI server, validate client-supplied messages, state, tools, and forwarded properties, and filter sensitive tool or agent output before streaming it back.
28	- Middleware, function-tool, migration, support, troubleshooting, upgrade, durable-agent, observability, and AG-UI pages all changed in the same review window. Check the exact current .NET page before relying on a Python example or an older preview signature.
29
30	## Architecture
31
32	```mermaid
33	flowchart LR
34	A["Task"] --> B{"Deterministic code is enough?"}
35	B -->\|Yes\| C["Write normal .NET code or a plain workflow"]
36	B -->\|No\| D{"One dynamic decision-maker is enough?"}
37	D -->\|Yes\| E["Use an `AIAgent` / `ChatClientAgent`"]
38	D -->\|No\| F["Use a typed `Workflow`"]
39	F --> G{"Needs durable Azure hosting or week-long execution?"}
40	G -->\|Yes\| H["Use durable agents on Azure Functions"]
41	G -->\|No\| I["Use in-process workflows"]
42	E --> J{"Need a remote protocol or UI?"}
43	F --> J
44	J -->\|OpenAI-compatible HTTP\| K["ASP.NET Core Hosting.OpenAI"]
45	J -->\|Agent-to-agent protocol\| L["A2A hosting"]
46	J -->\|Web UI protocol\| M["AG-UI"]
47	J -->\|Local debug shell\| N["DevUI (dev only)"]
48	```
49
50	## Core Knowledge
51
52	- `AIAgent` is the common runtime abstraction. It should stay mostly stateless.
53	- `AgentThread` still anchors most persisted conversation guidance,

People who liked this also viewed

6 picks

Type