exemplar-harness-sdk

Python SDK for Exemplar: session ingest, long-term memory, skills, prompts, HITL, and Relay policy adapters for runtime agent SDKs.

Quick start covers Agno, OpenAI SDK, Google ADK, and Claude Agent SDK. More frameworks — see Framework extras. Relay policy adapters — see Relay policy and examples/relay/.

Related package: terminal CLI — exemplar-cli (docs, examples).

Install
Quick start
- Agno
  - Session ingest
  - Memory
  - Skills
  - Prompts
- OpenAI SDK
  - Session ingest
  - Memory
  - Skills
  - Prompts
- Google ADK
  - Session ingest
  - Memory
  - Skills
  - Prompts
- Claude Agent SDK
  - Session ingest
  - Memory
  - Skills
  - Prompts
Session ingest
- Example 1 — Framework helper (Agno)
- Example 2 — Direct ingest (no framework)
Memory
- Example 1 — Add and recall
- Example 2 — Search and update
Skills
- Example 1 — Create and list
- Example 2 — Get and search
Prompts
HITL (human-in-the-loop)
Relay policy
- Per-SDK examples
- Hook-free evaluate
CLI (separate package)
Advanced usage
Framework extras
Reference
- Optional install extras
- Envelope v1

Install

pip install exemplar-harness-sdk

# One agent framework (pick what you use)
pip install "exemplar-harness-sdk[agno]"
pip install "exemplar-harness-sdk[openai]"
pip install "exemplar-harness-sdk[google-adk]"
pip install "exemplar-harness-sdk[claude-agent]"

# Everything
pip install "exemplar-harness-sdk[all]"

export EXEMPLAR_API_KEY="eis_your_org_api_key"

Licensed for non-commercial use only. Commercial use requires a separate license from Exemplar Dev LLC. See LICENSE.

Quick start

Pick your agent framework below. Each section shows session ingest, memory, skills, and prompts for that stack.

Reuse the same session_id for every turn in a conversation. Session helpers call Harness.ingest() for you (Google ADK: call ingest_adk_session after the run). Skills and prompts are shared platform APIs — wire them into your agent with the patterns below.

flowchart LR
  Agent[Your agent] --> Integration[SDK integration]
  Integration --> Harness[Harness.ingest]
  Harness --> API[Exemplar platform API]
  API --> Eval[Harness eval]

Agno

pip install "exemplar-harness-sdk[agno]"

Session ingest

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from exemplar_harness import Harness
from exemplar_harness.integrations.agno import harness_agno_post_hook

harness = Harness.from_env()
agent = Agent(
    name="support-bot",
    model=OpenAIChat(id="gpt-4o"),
    post_hooks=[
        harness_agno_post_hook(
            harness,
            session_id="sess-abc",
            agent_id="support-bot",
            source_app="my-app",
        )
    ],
)
agent.run("Summarize our refund policy.")

Relay policy (tool hooks)

Same Harness client — share agent_id / session_id with ingest. Full per-SDK demos: examples/relay/.

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from exemplar_harness import Harness
from exemplar_harness.integrations.agno import harness_agno_post_hook

harness = Harness.from_env(agent_id="support-bot")
relay = harness.relay(surface="agno", source_app="my-app")

def get_weather(city: str) -> str:
    """Return a short weather summary for the city."""
    return f"Sunny in {city}"

agent = Agent(
    name="support-bot",
    model=OpenAIChat(id="gpt-4o"),
    tools=[get_weather],
    tool_hooks=[relay.agno_tool_hook(session_id="sess-abc")],
    post_hooks=[
        harness_agno_post_hook(
            harness,
            session_id="sess-abc",
            agent_id="support-bot",
            source_app="my-app",
        )
    ],
)

Runnable example: examples/relay/agno.py

Memory

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from exemplar_harness import Harness
from exemplar_harness.integrations.agno import harness_agno_post_hook
from exemplar_harness.integrations.memory.agno import (
    make_agno_memory_helper,
    harness_agno_memory_hooks,
)

harness = Harness.from_env()
mem = make_agno_memory_helper(
    harness, user_id="user-123", session_id="sess-abc", app_id="my-app"
)
pre, post = harness_agno_memory_hooks(mem)

agent = Agent(
    name="support-bot",
    model=OpenAIChat(id="gpt-4o"),
    pre_hooks=[pre],
    post_hooks=[
        post,
        harness_agno_post_hook(harness, session_id="sess-abc", agent_id="support-bot"),
    ],
)
agent.run("What do you know about my formatting preferences?")

Live example: examples/live/agno_memory_demo.py

Skills

Install the skill folder for Agent Skills–compatible runtimes (SKILL.md + files). Prompt-injection frameworks can also pass skill.instructions (markdown body only).

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from exemplar_harness import Harness

harness = Harness.from_env()
skills = harness.skills()

# Folder-first: dest/<name>/SKILL.md (+ references/, scripts/, assets/)
skills.install(".agents/skills", names=["refund-policy"])

skill = skills.get("refund-policy")
agent = Agent(
    name="support-bot",
    model=OpenAIChat(id="gpt-4o"),
    instructions=[skill.instructions],
)
agent.run("Can a customer return an item after 20 days?")

Live example: examples/live/agno_skills_demo.py

Prompts

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from exemplar_harness import Harness

harness = Harness.from_env()
built = harness.prompts().build("support-summary", variables={"topic": "returns"})

system = next((m["content"] for m in built.messages if m["role"] == "system"), "")
user = next((m["content"] for m in built.messages if m["role"] == "user"), "")

agent = Agent(
    name="support-bot",
    model=OpenAIChat(id="gpt-4o"),
    instructions=[system] if system else None,
)
agent.run(user)

OpenAI SDK

pip install "exemplar-harness-sdk[openai]"

Session ingest

from openai import OpenAI
from exemplar_harness import Harness
from exemplar_harness.integrations.openai import HarnessOpenAICallback, sdk_chat_completion

harness = Harness.from_env()
callback = HarnessOpenAICallback(
    harness,
    session_id="sess-abc",
    agent_id="support-bot",
    source_app="my-app",
)
client = OpenAI()
sdk_chat_completion(
    harness,
    callback,
    client,
    model="gpt-4o",
    messages=[{"role": "user", "content": "Summarize our refund policy."}],
)

Memory

from openai import OpenAI
from exemplar_harness import Harness
from exemplar_harness.integrations.memory.openai import (
    make_openai_memory_helper,
    sdk_chat_completion_with_memory,
)

harness = Harness.from_env()
helper = make_openai_memory_helper(
    harness, user_id="user-123", session_id="sess-abc", app_id="my-app"
)
client = OpenAI()
sdk_chat_completion_with_memory(
    helper,
    client,
    model="gpt-4o",
    messages=[{"role": "user", "content": "What do you know about my formatting preferences?"}],
)

Live example: examples/live/openai_memory_demo.py

Skills

from openai import OpenAI
from exemplar_harness import Harness

harness = Harness.from_env()
skills = harness.skills()
skills.install(".agents/skills", names=["refund-policy"])

skill = skills.get("refund-policy")
client = OpenAI()
client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": skill.instructions},
        {"role": "user", "content": "Can a customer return an item after 20 days?"},
    ],
)

Live example: examples/live/openai_skills_demo.py

Relay policy

OpenAI Agents SDK (not Chat Completions) uses tool guardrails:

harness = Harness.from_env(agent_id="support-bot")
relay = harness.relay(surface="openai_agents", source_app="my-app")
# Agent(..., tool_input_guardrails=[relay.openai_tool_input(session_id=...)],
#            tool_output_guardrails=[relay.openai_tool_output(session_id=...)])

Runnable example: examples/relay/openai_agents.py

Prompts

from openai import OpenAI
from exemplar_harness import Harness
from exemplar_harness.integrations.openai import HarnessOpenAICallback, sdk_chat_completion

harness = Harness.from_env()
built = harness.prompts().build("support-summary", variables={"topic": "returns"})
callback = HarnessOpenAICallback(harness, session_id="sess-abc", agent_id="support-bot")
client = OpenAI()
sdk_chat_completion(
    harness,
    callback,
    client,
    model=built.model or "gpt-4o",
    messages=built.messages,
)

Google ADK

pip install "exemplar-harness-sdk[google-adk]"

Session ingest

import asyncio

from exemplar_harness import Harness
from exemplar_harness.integrations.google_adk import ingest_adk_session
from google.adk.agents import LlmAgent
from google.adk.runners import Runner
from google.adk.sessions import InMemorySessionService
from google.genai import types

harness = Harness.from_env()
session_id, app_name, user_id = "sess-abc", "my_app", "user-1"

agent = LlmAgent(
    model="gemini-2.5-flash",
    name="support_bot",  # must be a valid Python identifier
    instruction="Answer concisely.",
)
sessions = InMemorySessionService()


async def run_and_ingest() -> None:
    await sessions.create_session(app_name=app_name, user_id=user_id, session_id=session_id)
    runner = Runner(agent=agent, app_name=app_name, session_service=sessions)
    message = types.Content(role="user", parts=[types.Part(text="Summarize our refund policy.")])
    async for _ in runner.run_async(user_id=user_id, session_id=session_id, new_message=message):
        pass
    session = await sessions.get_session(app_name=app_name, user_id=user_id, session_id=session_id)
    ingest_adk_session(
        harness,
        session.model_dump(mode="json", exclude_none=True),
        session_id=session_id,
        agent_id="support-bot",
        source_app="my-app",
    )


asyncio.run(run_and_ingest())

Memory

from exemplar_harness import Harness
from exemplar_harness.integrations.memory.google_adk import (
    make_google_adk_memory_helper,
    prepare_user_message,
    record_session_turn_with_memory,
)

harness = Harness.from_env()
mem = make_google_adk_memory_helper(
    harness, user_id="user-123", session_id="sess-abc", app_id="my-app"
)

question = "What do you know about my formatting preferences?"
user_text = prepare_user_message(mem, question)
# ... run your ADK agent with user_text, capture model_response ...
# record_session_turn_with_memory(mem, user_message=question, model_response=model_response)

Live example: examples/live/google_adk_memory_demo.py

Skills

from exemplar_harness import Harness
from google.adk.agents import LlmAgent

harness = Harness.from_env()
skills = harness.skills()
skills.install(".agents/skills", names=["refund-policy"])

skill = skills.get("refund-policy")
agent = LlmAgent(
    model="gemini-2.5-flash",
    name="support_bot",
    instruction=skill.instructions,
)

Live example: examples/live/google_adk_skills_demo.py

Relay policy

harness = Harness.from_env(agent_id="support-bot")
relay = harness.relay(surface="adk", source_app="my-app")
agent = LlmAgent(
    model="gemini-2.5-flash",
    name="support_bot",
    tools=[...],
    before_tool_callback=relay.adk_before_tool(session_id="sess-abc"),
    after_tool_callback=relay.adk_after_tool(session_id="sess-abc"),
)

Runnable example: examples/relay/adk.py

Prompts

from exemplar_harness import Harness
from google.adk.agents import LlmAgent
from google.genai import types

harness = Harness.from_env()
built = harness.prompts().build("support-summary", variables={"topic": "returns"})

system = next((m["content"] for m in built.messages if m["role"] == "system"), "Answer concisely.")
user = next((m["content"] for m in built.messages if m["role"] == "user"), "")

agent = LlmAgent(model="gemini-2.5-flash", name="support_bot", instruction=system)
message = types.Content(role="user", parts=[types.Part(text=user)])
# pass `message` into Runner.run_async(...), then ingest_adk_session as above

Claude Agent SDK

pip install "exemplar-harness-sdk[claude-agent]"

Session ingest

import asyncio

from exemplar_harness import Harness
from exemplar_harness.integrations.claude_agent import HarnessClaudeAgentHandler

harness = Harness.from_env()
handler = HarnessClaudeAgentHandler(
    harness,
    session_id="sess-abc",
    agent_id="support-bot",
    source_app="my-app",
)
asyncio.run(handler.run_query("Summarize our refund policy."))

Memory

import asyncio

from exemplar_harness import Harness
from exemplar_harness.integrations.claude_agent import HarnessClaudeAgentHandler
from exemplar_harness.integrations.memory.claude_agent import (
    make_claude_agent_memory_helper,
    prepare_prompt,
    record_agent_result_with_memory,
)

harness = Harness.from_env()
handler = HarnessClaudeAgentHandler(harness, session_id="sess-abc", agent_id="support-bot")
mem = make_claude_agent_memory_helper(
    harness, user_id="user-123", session_id="sess-abc", app_id="my-app"
)


async def run() -> None:
    question = "What do you know about my formatting preferences?"
    prompt = prepare_prompt(mem, question)
    result, _ = await handler.run_query(prompt)
    record_agent_result_with_memory(mem, prompt=question, result=result)


asyncio.run(run())

Live example: examples/live/claude_agent_memory_demo.py

Skills

import asyncio

from exemplar_harness import Harness
from exemplar_harness.integrations.claude_agent import (
    HarnessClaudeAgentHandler,
    merge_claude_agent_options,
)

harness = Harness.from_env()
skills = harness.skills()
# Claude Code also discovers folders under .claude/skills via CLI install/pull
skills.install(".claude/skills", names=["refund-policy"])

skill = skills.get("refund-policy")
handler = HarnessClaudeAgentHandler(harness, session_id="sess-abc", agent_id="support-bot")


async def run() -> None:
    from claude_agent_sdk import ClaudeAgentOptions

    options = merge_claude_agent_options(
        handler,
        ClaudeAgentOptions(system_prompt=skill.instructions),
    )
    await handler.run_query("Can a customer return an item after 20 days?", options=options)


asyncio.run(run())

Live example: examples/live/claude_agent_skills_demo.py

Relay policy

from claude_agent_sdk import ClaudeAgentOptions

harness = Harness.from_env(agent_id="support-bot")
relay = harness.relay(surface="claude_sdk", source_app="my-app")
options = ClaudeAgentOptions(
    hooks=relay.claude_hooks(session_id="sess-abc"),
)

Runnable example: examples/relay/claude_sdk.py

Prompts

import asyncio

from exemplar_harness import Harness
from exemplar_harness.integrations.claude_agent import (
    HarnessClaudeAgentHandler,
    merge_claude_agent_options,
)

harness = Harness.from_env()
built = harness.prompts().build("support-summary", variables={"topic": "returns"})
system = next((m["content"] for m in built.messages if m["role"] == "system"), "")
user = next((m["content"] for m in built.messages if m["role"] == "user"), "")
handler = HarnessClaudeAgentHandler(harness, session_id="sess-abc", agent_id="support-bot")


async def run() -> None:
    from claude_agent_sdk import ClaudeAgentOptions

    options = merge_claude_agent_options(
        handler,
        ClaudeAgentOptions(system_prompt=system or None),
    )
    await handler.run_query(user, options=options)


asyncio.run(run())

Session ingest

Base helper: Harness.ingest() / framework helpers above.

Example 1 — Framework helper (Agno)

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from exemplar_harness import Harness
from exemplar_harness.integrations.agno import harness_agno_post_hook

harness = Harness.from_env()
agent = Agent(
    name="support-bot",
    model=OpenAIChat(id="gpt-4o"),
    post_hooks=[harness_agno_post_hook(harness, session_id="sess-abc", agent_id="support-bot")],
)
agent.run("What is the return window?")

Example 2 — Direct ingest (no framework)

from exemplar_harness import Harness

harness = Harness.from_env()
harness.ingest(
    "generic",
    session_id="sess-abc",
    event="turns",
    data={
        "turns": [
            {
                "input": "What is harness eval?",
                "output": "Automated judge over agent sessions.",
                "model": "gpt-4o",
            }
        ]
    },
    agent_id="my-agent",
    source_app="my-app",
)

Parameter	Purpose
`session_id`	Groups turns into one eval session
`agent_id`	Agent id on the ingest body (`agentId`); set on `Harness(..., agent_id=...)` to also send `X-Harness-Agent-Id` on MCP tool calls
`source_app`	Your application name
`auto_judge_run`	Run harness judge after ingest (`True` / `False` / omit)

Memory

Base helper: harness.memory(...).

Example 1 — Add and recall

from exemplar_harness import Harness

harness = Harness.from_env()
memory = harness.memory(user_id="user-123", session_id="chat-abc", app_id="my-app")

memory.add("User prefers bullet-point answers.", memory_type="preference")
context = memory.recall("how should I format answers?", format="markdown")

Example 2 — Search modes and formats

results = memory.search(
    "formatting preferences",
    top_k=5,
    search_mode="hybrid",
    format="json",
)
envelope = memory.search_envelope("theme", format="toon", search_mode="hybrid")
# envelope.body → prompt injection; envelope.records → structured hits

listed = memory.list(limit=20)
record = memory.get(listed[0].memory_id)
memory.update(record.memory_id, content="User prefers numbered lists.")
memory.delete(record.memory_id)

Skills

Base helper: harness.skills().

Example 1 — Create and list

from exemplar_harness import Harness

harness = Harness.from_env()
skills = harness.skills()

record = skills.create(
    name="refund-policy",
    instructions="# Refund policy\n\nReturns within 30 days.\n\nSee [references/policy.md](references/policy.md).",
    description="Refund workflow",
    tags=["support"],
    files={"references/policy.md": "# Policy\n\n30-day returns.\n"},
)
items = skills.list(limit=20)

Example 2 — Get, search, and install

fetched = skills.get("refund-policy")  # by ID or unique name
hits = skills.search("refund", top_k=5)

# Materialize SKILL.md + supporting files for agent runtimes
skills.install(".agents/skills", names=["refund-policy"])

Prompts

Base helper: harness.prompts().

Example 1 — Create and run

from exemplar_harness import Harness

harness = Harness.from_env()
prompts = harness.prompts()

record = prompts.create(
    name="support-summary",
    title="Support summary",
    messages=[
        {"role": "system", "content": "Be concise."},
        {"role": "user", "content": "Summarize topic: {{topic}}."},
    ],
    variables=["topic"],
)
result = prompts.run("support-summary", variables={"topic": "returns"})
print(result["content"])

Example 2 — Build for your own agent framework

Fetch a stored prompt, substitute {{variables}} locally, and hand messages to LangGraph, OpenAI, Haystack, etc. Does not call Exemplar’s model runner.

built = prompts.build("support-summary", variables={"topic": "returns"})
# built.messages -> [{"role": "system", ...}, {"role": "user", ...}]
# built.model    -> default model from the registry (if set)
# pass built.messages into your framework / LLM client

Or reuse an already-fetched record (no second network call):

record = prompts.get("support-summary")
built = record.build(variables={"topic": "returns"})

Example 3 — List and get

listed = prompts.list(limit=20)
fetched = prompts.get("support-summary")  # by ID or unique name
hits = prompts.search("support", top_k=5)

HITL (human-in-the-loop)

Base helper: harness.hitl(). Lets an agent pause mid-workflow and wait for a human decision. Requests appear in the console under Agent Harness → HITL Approvals, where a reviewer approves, rejects, answers, or picks an option. Blocking wait uses polling; there are no webhooks.

Production reviewers should resolve requests in the console (or with reviewer-scoped credentials). Do not have the agent runtime self-approve via /respond with the same org API key — that pattern is demo-only.

Example 1 — Approval gate (create + wait in one call)

from exemplar_harness import Harness, HITLTimeoutError

harness = Harness.from_env(agent_id="deploy-agent")
hitl = harness.hitl()

try:
    result = hitl.ask(
        "Deploy build 1234 to production?",
        description="All checks green. Blast radius: payments service.",
        payload={"build": "1234", "service": "payments"},
        ttl_seconds=1800,   # server-side expiry
        timeout=1800,       # local wait budget (seconds)
        poll_interval=5,
    )
except HITLTimeoutError:
    result = None

if result and result.approved:
    deploy()
elif result and result.state == "rejected":
    print(f"Rejected: {result.response.comment}")

Example 2 — Free-text input and single choice

answer = hitl.ask("Which rollback strategy?", request_type="input")
print(answer.response.text)

choice = hitl.ask(
    "Pick a deployment region",
    request_type="select",
    options=["us-east-1", "eu-west-1"],
)
print(choice.response.option)

Example 3 — Non-blocking create, check later, cancel

request = hitl.request_approval("Rotate production credentials?")

status = hitl.get(request.request_id)   # non-blocking status check
if status.is_pending:
    hitl.cancel(request.request_id)     # e.g. the run was aborted

Example 4 — As a tool in any agent framework

Plain sync methods — wrap them in a tool function for LangChain, Agno, CrewAI, OpenAI, etc.

from langchain_core.tools import tool

@tool
def ask_human_approval(question: str) -> str:
    """Ask a human operator to approve or reject an action."""
    result = harness.hitl().ask(question, timeout=900)
    if result.approved:
        return "approved"
    return f"denied ({result.state}): {result.response.comment or 'no comment'}"

Relay policy

Defaults to fail-closed (fail_open=False): if Relay is unreachable, decide/evaluate raise instead of allowing the tool. Pass fail_open=True only when you explicitly prefer availability over enforcement.

Index and run instructions: examples/relay/README.md.

HARNESS_EXAMPLES_SIMULATED=1 python -m examples.relay.run_all
HARNESS_EXAMPLES_SIMULATED=1 python -m examples.relay.run_all --list
EXEMPLAR_API_KEY=... python -m examples.relay.evaluate

Per-SDK examples

Surface	Adapter	Example
Agno	`relay.agno_tool_hook`	`examples/relay/agno.py`
Claude Agent SDK	`relay.claude_hooks`	`examples/relay/claude_sdk.py`
Google ADK	`relay.adk_before_tool` / `adk_after_tool`	`examples/relay/adk.py`
OpenAI Agents	`relay.openai_tool_input` / `openai_tool_output`	`examples/relay/openai_agents.py`
LangChain	`relay.langchain_middleware`	`examples/relay/langchain.py`
LangGraph	`relay.langgraph_middleware`	`examples/relay/langgraph.py`
Pydantic AI	`relay.pydantic_ai_hooks`	`examples/relay/pydantic_ai.py`
CrewAI	`relay.crewai_hooks` / `crewai_register`	`examples/relay/crewai.py`
Semantic Kernel	`relay.semantic_kernel_filter` / `semantic_kernel_register`	`examples/relay/semantic_kernel.py`

Hook-free evaluate

CI / preflight / custom runtimes — same Control + Enforcement stack, no SDK hooks:

from exemplar_harness import Harness
from exemplar_harness.relay import RelayDecision

harness = Harness.from_env(agent_id="support-bot")
relay = harness.relay(surface="agno", source_app="my-app")

verdict = relay.evaluate(
    tool_name="shell",
    arguments={"command": "rm -rf /tmp/x"},
    user_id="user_123",
)
if verdict.decision is RelayDecision.DENY:
    raise RuntimeError(verdict.reason)

relay.evaluate_path(path=".env")
relay.evaluate_bash(command="ls -la")

Runnable example: examples/relay/evaluate.py

CLI (separate package)

Skills, prompts, and memory are also available as a standalone terminal package — not bundled with this SDK:


PyPI	`exemplar-cli`
Docs	`exemplar-cli/README.md`
Examples	`examples/cli/README.md`

pip install exemplar-cli
export EXEMPLAR_API_KEY="eis_your_org_api_key"
exemplar doctor

Advanced usage

One advanced pattern per offering. For full framework wiring, see examples/live/.

Session ingest — Session helper with auto judge

from exemplar_harness import Harness

harness = Harness.from_env()
session = harness.session(
    "sess-abc",
    agent_id="support-bot",
    source_app="my-app",
    auto_judge_run=True,  # run judge after each ingest through this session
)
session.ingest(
    "generic",
    event="turns",
    data={"turns": [{"input": "Hello", "output": "Hi!", "model": "gpt-4o"}]},
)

Memory — Generic hook in any agent loop

from exemplar_harness import Harness
from exemplar_harness.integrations.memory import MemoryHook

harness = Harness.from_env()
memory = harness.memory(user_id="user-123", session_id="chat-abc", app_id="my-app")
hook = MemoryHook(memory, recall_top_k=5, auto_add=False)

user_input = "What do you know about me?"
recall = hook.before_turn(user_input)  # prepend to system prompt
# ... run LLM ...
hook.after_turn(user_input, assistant_output)  # no-op unless auto_add=True

Skills — Install folders for agent runtimes

A skill is a directory rooted at SKILL.md (plus optional references/, scripts/, assets/). Install the whole folder for Cursor, Claude Code, ADK, Agno, Deep Agents, AG2, CrewAI, and similar agents — do not treat record.instructions as the full skill (that field is the markdown body only, useful for quick editor/MCP use).

Live skills demos also cover framework-native loaders:

Deep Agents: examples/live/deepagents_skills_demo.py (create_deep_agent(..., skills=[...]))
AG2: examples/live/ag2_skills_demo.py (SkillPlugin)
CrewAI: examples/live/crewai_skills_demo.py (Agent(..., skills=[...]))
Agno / OpenAI / Google ADK / Claude Agent: see Quick start sections above

from exemplar_harness import Harness

skills = Harness.from_env().skills()

# Materialize all active skills: dest/<name>/SKILL.md + supporting files
paths = skills.install(".agents/skills")

# Or one skill into Cursor project skills
skills.install(".cursor/skills", names=["refund-policy"])

CLI equivalent: exemplar skills install --all --dest .agents/skills (alias of pull).

Prompts — Publish, build for frameworks, or run inline

from exemplar_harness import Harness

prompts = Harness.from_env().prompts()

prompts.publish_version(
    "support-summary",
    messages=[
        {"role": "system", "content": "Be concise."},
        {"role": "user", "content": "Bullet summary for: {{topic}}."},
    ],
    change_notes="Use bullets",
)

# Hand off to your agent framework (local {{var}} substitution)
built = prompts.build("support-summary", variables={"topic": "returns"})

# Or execute via Exemplar without a stored prompt
inline = prompts.run_inline(
    messages=[
        {"role": "system", "content": "Be concise."},
        {"role": "user", "content": "Say hello."},
    ],
    model="openai/gpt-4o-mini",
)

Framework extras

Framework	Extra	Wire this
LangChain	`langchain`	`make_langchain_callback_handler` → `callbacks=[handler]`
LangGraph	`langgraph`	`HarnessLangGraphHandler.make_graph_callback_handler()`
Deep Agents	`deepagents`	`HarnessDeepAgentsHandler.make_graph_callback_handler()` / `record_run`
LiteLLM	`litellm`	`register_litellm_handler` + `metadata={"session_id": ...}`
OpenAI SDK	`openai`	`HarnessOpenAICallback.on_completion`
Anthropic SDK	`anthropic`	`make_anthropic_middleware`
Claude Agent SDK	`claude-agent`	`HarnessClaudeAgentHandler.run_query`
Portkey	`portkey`	`HarnessPortkeyCallback.on_completion`
Agno	`agno`	`harness_agno_post_hook` → `Agent.post_hooks`
Haystack	`haystack`	`HarnessHaystackHandler.run_and_record`
LlamaIndex	`llamaindex`	`register_llamaindex_handler`
AutoGen	`autogen`	`HarnessAutoGenHandler.on_agent_run_complete`
AG2	`ag2`	`HarnessAG2Handler.record_ask` / `record_chat_turn`
CrewAI	`crewai`	`make_crewai_listener`
Google GenAI SDK	`google-genai`	`instrument_google_genai_client`
Google ADK	`google-adk`	`ingest_adk_session`
Pydantic AI	`pydantic-ai`	`instrument_pydantic_ai_agent`
Semantic Kernel	`semantic-kernel`	`register_semantic_kernel_filter`
smolagents	`smolagents`	`harness_smolagents_step_callback`

Matching memory helpers live under exemplar_harness.integrations.memory.*. Relay policy adapters: examples/relay/ (python -m examples.relay.run_all).

# List / run live demos
python -m examples.live.run_all --list
python -m examples.live.run_memory_demos --list
python -m examples.live.run_platform_demos --list
HARNESS_EXAMPLES_SIMULATED=1 python -m examples.live.run_memory_demos --only memory_agno
HARNESS_EXAMPLES_SIMULATED=1 python -m examples.live.run_platform_demos --only skills_openai
HARNESS_EXAMPLES_SIMULATED=1 python -m examples.relay.run_all

Reference

Optional install extras

Extra	Module
`langchain`	`exemplar_harness.integrations.langchain`
`langgraph`	`exemplar_harness.integrations.langgraph`
`deepagents`	`exemplar_harness.integrations.deepagents`
`litellm`	`exemplar_harness.integrations.litellm`
`openai`	`exemplar_harness.integrations.openai`
`anthropic`	`exemplar_harness.integrations.anthropic`
`claude-agent`	`exemplar_harness.integrations.claude_agent`
`portkey`	`exemplar_harness.integrations.portkey`
`agno`	`exemplar_harness.integrations.agno`
`haystack`	`exemplar_harness.integrations.haystack`
`llamaindex`	`exemplar_harness.integrations.llamaindex`
`autogen`	`exemplar_harness.integrations.autogen`
`ag2`	`exemplar_harness.integrations.ag2`
`crewai`	`exemplar_harness.integrations.crewai`
`google-adk`	`exemplar_harness.integrations.google_adk`
`google-genai`	`exemplar_harness.integrations.google_genai`
`pydantic-ai`	`exemplar_harness.integrations.pydantic_ai`
`semantic-kernel`	`exemplar_harness.integrations.semantic_kernel`
`smolagents`	`exemplar_harness.integrations.smolagents`

Vercel AI SDK is not included in the Python package (TypeScript SDK path).

Envelope v1

Each ingest POSTs schemaVersion: 1 to POST /api/harness-ingest/v1/sessions with a sourceType and framework-native data payload. The Exemplar platform API maps envelopes to eval session turns. Harness judge runs use POST /api/harness-judge/v1/runs; per-turn session eval uses POST /api/harness-session-eval/v1/sessions/{sessionId}.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

exemplar_harness_sdk-0.2.21.tar.gz (70.8 kB view details)

Uploaded Aug 8, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

exemplar_harness_sdk-0.2.21-py3-none-any.whl (111.8 kB view details)

Uploaded Aug 8, 2026 Python 3

File details

Details for the file exemplar_harness_sdk-0.2.21.tar.gz.

File metadata

Download URL: exemplar_harness_sdk-0.2.21.tar.gz
Upload date: Aug 8, 2026
Size: 70.8 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: poetry/1.8.2 CPython/3.12.4 Darwin/24.5.0

File hashes

Hashes for exemplar_harness_sdk-0.2.21.tar.gz
Algorithm	Hash digest
SHA256	`1e06e37885ee3277c3d2208fb62934bf2301484841ce655846b88fe611607f85`
MD5	`411ed83d20318dfd24ec8881e03ba632`
BLAKE2b-256	`9a44c148129424abfe97dad39fe834330f18f96984f5083fdaaaf30a71dd28b1`

See more details on using hashes here.

File details

Details for the file exemplar_harness_sdk-0.2.21-py3-none-any.whl.

File metadata

Download URL: exemplar_harness_sdk-0.2.21-py3-none-any.whl
Upload date: Aug 8, 2026
Size: 111.8 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: poetry/1.8.2 CPython/3.12.4 Darwin/24.5.0

File hashes

Hashes for exemplar_harness_sdk-0.2.21-py3-none-any.whl
Algorithm	Hash digest
SHA256	`2564be104e181857ba578ae0f77a9141602bdb918c6d1e69283fb749a4b65ba3`
MD5	`27b2f1853a9871ef7f9133b5b97cd8f2`
BLAKE2b-256	`d5fcafc33acda2e8d48cbc2cdd035061361e51f8e940674e2a625da2ad8dc1d8`

See more details on using hashes here.

Release history Release notifications | RSS feed

0.2.22

Aug 15, 2026

This release

0.2.21

Aug 8, 2026

0.2.20

Aug 8, 2026

0.2.19

Aug 8, 2026

0.2.18

Aug 8, 2026

0.2.17

Jul 24, 2026

0.2.16

Jul 20, 2026

0.2.15

Jul 20, 2026

0.2.14

Jul 15, 2026

0.2.13

Jul 15, 2026

0.2.12

Jul 15, 2026

0.2.11

Jul 15, 2026

0.2.10

Jul 15, 2026

0.2.9

Jul 14, 2026

0.2.8

Jul 6, 2026

0.2.7

Jul 6, 2026

0.2.6

Jul 6, 2026

0.2.5

Jul 6, 2026

0.2.4

Jul 4, 2026

0.2.3

Jul 3, 2026

0.2.2

Jun 29, 2026

0.2.1

Jun 29, 2026

0.2.0

Jun 25, 2026

0.1.2

Jun 25, 2026

0.1.1

Jun 25, 2026

0.1.0

Jun 25, 2026

exemplar-harness-sdk 0.2.21

exemplar-harness-sdk

Contents

Install

Quick start

Agno

Session ingest

Relay policy (tool hooks)

Memory

Skills

Prompts

OpenAI SDK

Session ingest

Memory

Skills

Relay policy

Prompts

Google ADK

Session ingest

Memory

Skills

Relay policy

Prompts

Claude Agent SDK

Session ingest

Memory

Skills

Relay policy

Prompts

Session ingest

Example 1 — Framework helper (Agno)

Example 2 — Direct ingest (no framework)

Memory

Example 1 — Add and recall

Example 2 — Search modes and formats

Skills

Example 1 — Create and list

Example 2 — Get, search, and install

Prompts

Example 1 — Create and run

Example 2 — Build for your own agent framework

Example 3 — List and get

HITL (human-in-the-loop)

Example 1 — Approval gate (create + wait in one call)

Example 2 — Free-text input and single choice

Example 3 — Non-blocking create, check later, cancel

Example 4 — As a tool in any agent framework

Relay policy

Per-SDK examples

Hook-free evaluate

CLI (separate package)

Advanced usage

Session ingest — Session helper with auto judge

Memory — Generic hook in any agent loop

Skills — Install folders for agent runtimes

Prompts — Publish, build for frameworks, or run inline

Framework extras

Reference

Optional install extras

Envelope v1

Project links

Key dates

1 maintainer

Credits

License

Requires

Tags

Classifiers

Download files

Source Distribution

Built Distribution

File details

File metadata

File hashes

File details

File metadata

File hashes

Release history Release notifications | RSS feed