Hindsight.AgentFramework.Net 0.1.0

Hindsight.AgentFramework.Net

Long-term memory for Microsoft Agent Framework agents, backed by a Hindsight memory bank.

Attach one AIContextProvider and memory happens on its own, every turn:

• before each run — memories relevant to the user's message are recalled from the bank and injected into the agent's instructions;
• after each run — the turn's transcript is retained, so future runs build on it.

No MCP server. No tool the model has to remember to call.

This is an independent, community .NET port of Vectorize's Python package hindsight-agent-framework. It is not affiliated with, endorsed by, or supported by Vectorize AI, Inc. — please raise issues here, not on their tracker. It is also unrelated to the similarly-named Hindsight.Behave package, which is a behaviour-tree library by a different author. See NOTICE.

Install

dotnet add package Hindsight.AgentFramework.Net

Targets net8.0 and net10.0.

Use

using Hindsight.AgentFramework;

using var http = new HttpClient();
var client = new HindsightClient(http, new HindsightOptions
{
    ApiKey = Environment.GetEnvironmentVariable("HINDSIGHT_API_KEY"),
});

var memory = new HindsightMemoryProvider(client, new HindsightOptions
{
    BankId = "user-123",           // one bank per user is the usual shape
    Mission = "Remember this user's preferences and ongoing projects.",
});

AIAgent agent = chatClient.CreateAIAgent(new ChatClientAgentOptions
{
    Name = "assistant",
    Instructions = "You are a helpful assistant.",
    AIContextProviderFactory = _ => memory,
});

With dependency injection

builder.Services.AddHttpClient<IHindsightClient, HindsightClient>()
    .ConfigureHttpClient(c => c.Timeout = TimeSpan.FromSeconds(30));

Then resolve IHindsightClient and build a HindsightMemoryProvider per user, giving each its own BankId.

Options

IsEnabled is a delegate on purpose

A provider is typically built once and reused across many runs, while "should this particular exchange be remembered?" is a per-run question — an incognito or off-the-record conversation, a user who has opted out, a health-check run. Capturing that decision as a value at construction would be wrong on every later run. IsEnabled is read at invoke time:

new HindsightOptions { BankId = userId, IsEnabled = () => !conversationIsEphemeral }

Behaviour worth knowing

• Nothing here can break your agent. Every recall and retain is wrapped; a failure is logged at debug and swallowed. A memory outage degrades the agent to no memory, never to an exception.
• Retain is sent with async: true. Hindsight's retain performs LLM fact extraction inline otherwise, which would stall the turn by seconds while the agent waits.
• A failed run is not retained. If InvokedContext.InvokeException is set, the transcript is dropped — a broken turn is not a memory worth keeping. (The Python original has no equivalent; its context provider API exposes no such signal.)
• No feedback loop. Recalled memories are injected as AIContext.Instructions, which the framework composes into a per-run copy of the agent's options. They never become messages, so they are not visible to retain and are never written back to the bank.

What is implemented

Recall, retain, create-bank and health. Hindsight's other surfaces — reflect, entities, mental models, knowledge base, documents, directives, observations — are out of scope, as is deleting or inspecting memories.

Releasing

Tag a commit vX.Y.Z and push it. .github/workflows/release.yml tests, packs with the version taken from the tag, and publishes to nuget.org using trusted publishing — there is no long-lived API key stored in this repository. The trusted publishing policy on nuget.org names this owner, this repository, and the workflow file release.yml; the only repository secret is NUGET_USER, the nuget.org profile name (not an email address).

Licence

MIT — see LICENSE. Portions derived from https://github.com/vectorize-io/hindsight (MIT, Copyright (c) 2025 Vectorize AI, Inc.); the full upstream notice is reproduced in NOTICE.