OllamaSharp is a .NET library that lets applications communicate with the Ollama API, which runs and manages language models locally or remotely. It is for .NET developers building applications that chat with models, create embeddings, manage models, stream responses, or use model tools and vision features.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/awaescher/ollamasharp/agents-mdgit clone --depth 1 https://github.com/awaescher/OllamaSharpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/awaescher/ollamasharp/agents-md)<a href="https://agentmods.dev/instructions/awaescher/ollamasharp/agents-md"><img src="https://agentmods.dev/badge/instructions/awaescher/ollamasharp/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03427 | $0.03427 |
| Opus 5 | $0.01714 | $0.01714 |
| Sonnet 5 | $0.00685 | $0.00685 |
| Haiku 4.5 | $0.00343 | $0.00343 |
Grade A, and why
OllamaSharp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — OllamaSharp
Project Overview
OllamaSharp is a C# .NET library providing bindings for the Ollama API. It targets
netstandard2.0, netstandard2.1, net8.0, net9.0, and net10.0. The library
implements IChatClient and IEmbeddingGenerator from Microsoft.Extensions.AI. It
includes a Roslyn source generator ([OllamaTool]).
How OllamaSharp Fits in the .NET AI Ecosystem
OllamaSharp is designed to match the native Ollama API 1:1 — every endpoint is covered. However, when building more complex AI applications or solutions that may swap providers (OpenAI, Anthropic, Azure, Ollama, etc.), users should strongly consider layering standard frameworks on top:
-
Microsoft.Extensions.AI (MEAI) — A lightweight abstraction layer defining
IChatClientandIEmbeddingGenerator<T, TEmbedding>. OllamaSharp natively implements both interfaces, so it works as a drop-in MEAI provider. Using MEAI gives telemetry, dependency injection, middleware pipelines, and provider interchangeability for free. This is the recommended starting point for most applications. MEAI also provides its own function calling / tool use pipeline viaIChatClient— tools are defined asAIFunctioninstances and the framework handles the tool-call loop, JSON schema generation, and result marshalling automatically. For most tool-use scenarios, this is simpler and more portable than using OllamaSharp's native tool system directly. -
Microsoft Agent Framework (successor to Microsoft Semantic Kernel) — For advanced agentic scenarios with planning, memory, multi-agent orchestration, and sophisticated tool use. The Agent Framework goes further than MEAI by providing automatic tool-call orchestration across multiple turns, dependency-injected tool classes with state, retry policies, and multi-agent collaboration — all backed by the
IChatClientabstraction. OllamaSharp serves as the Ollama provider under the hood, meaning it doesn't become obsolete — it powers these frameworks.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 228 lines · 3,427 tokens per session scan A 7d7b33f88866
OllamaSharp AGENTS.md is an instructions file published in the GitHub repository awaescher/OllamaSharp (1,402 stars, last pushed 1mo ago), licensed MIT. It adds 3,427 tokens to every session, about $0.0171 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ollama AGENTS.md
AGENTS.md instructions for ollama/ollama, covering agents.md and building.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
SpawnDev.AI CLAUDE.md
Claude Code instructions for LostBeard/SpawnDev.AI, covering claude.md - spawndev.ai, layering (strict, no upward references), hard rules, diagnostics / env levers and verification.
LocalAI AGENTS.md
AGENTS.md instructions for mudler/LocalAI, covering localai agent instructions, policy for ai-assisted contributions, topics and quick reference.
lemonade AGENTS.md
AGENTS.md instructions for lemonade-sdk/lemonade, covering agents.md, project overview, architecture, executables and backend abstraction.
langwatch CLAUDE.md
Claude Code instructions for langwatch/langwatch, covering langwatch, before you implement anything, development environment, running with no container runtime and local dev by hostname — thuishaven / portless (recommended).