# Deep Agent – Persistent File System

**URL:** <https://forum.langchain.com/t/deep-agent-persistent-file-system/1720>\
**Category:** LangChain\
**Tags:** python-help\
**Created:** [October 1, 2025, 5:28pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720 "2025-10-01T17:28:22Z")\
**Posts on this page:** 11\
**Page:** 1

<div class="post-metadata">

**Author:** ![lreal](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/lreal/32/1158_2.png) [@lreal](https://forum.langchain.com/u/lreal)\
**Post date:** [October 1, 2025, 5:28pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/1 "2025-10-01T17:28:22Z")

</div>

How can we make the file system in Deep Agent persist, so it retains history updates throughout a single run?

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 1, 2025, 7:33pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/2 "2025-10-01T19:33:14Z")

</div>

Hi @lreal

I think you are looking for `checkpointer` funability - [Overview](https://langchain-ai.github.io/langgraph/concepts/persistence/#checkpoints)

Am I right?

---

<div class="post-metadata">

**Author:** ![lreal](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/lreal/32/1158_2.png) [@lreal](https://forum.langchain.com/u/lreal)\
**Post date:** [October 2, 2025, 5:30pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/3 "2025-10-02T17:30:05Z")

</div>

We have two sub-agents writing in parallel to `improved_code.txt`, but only the supervisor’s version is saved. How can we use a checkpointer to keep the full history instead of just the final overwrite? Could you show this in code?

thanks in advance

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 2, 2025, 5:34pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/4 "2025-10-02T17:34:32Z")

</div>

I don’t know how your subagents work. Could you please share the code?

---

<div class="post-metadata">

**Author:** ![lreal](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/lreal/32/1158_2.png) [@lreal](https://forum.langchain.com/u/lreal)\
**Post date:** [October 2, 2025, 6:10pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/5 "2025-10-02T18:10:34Z")

</div>

Here’s a minimal version of the code:

```auto

class CodeImproverState(TypedDict):
    messages: Annotated[list, operator.add]
    optimized_code: str
    readable_code: str
    final_code: str

def run_python_code(code: str):
    try:
        namespace = {}
        exec(code, namespace)
        return {"success": True, "output": "Code executed successfully"}
    except Exception as e:
        return {"success": False, "error": str(e)}

optimized_writer_instructions = """You are a code optimization expert.
Your task: Write optimized code to `improved_code.txt`
You can iterate and improve your code multiple times before handing off.
Each time you write, update the file with your improvements."""

readable_writer_instructions = """You are a code readability expert.
Your task: Write readable code to `improved_code.txt`
You can iterate and improve your code multiple times before handing off.
Each time you write, update the file with your improvements."""

judge_instructions = """You are the supervisor.
1. Call both sub-agents - they will write to `improved_code.txt` multiple times
2. After they finish, read `improved_code.txt` 
3. Write your final decision to `improved_code.txt`"""

optimized_writer = {
    "name": "Optimized Writer",
    "prompt": optimized_writer_instructions,
    "tools": [],
}

readable_writer = {
    "name": "Readable Writer",
    "prompt": readable_writer_instructions,
    "tools": [],
}

judge_agent = create_deep_agent(
    tools=[run_python_code],
    instructions=judge_instructions,
    model="gpt-4o-mini",
    subagents=[optimized_writer, readable_writer],
    state_schema=CodeImproverState,
).with_config({"recursion_limit": 200})

```

I used a checkpointer, but when the sub-agent runs multiple times, it doesn’t show the history.

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 2, 2025, 6:13pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/6 "2025-10-02T18:13:53Z")

</div>

Great, thank you. Let me see how it works.

---

<div class="post-metadata">

**Author:** ![lreal](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/lreal/32/1158_2.png) [@lreal](https://forum.langchain.com/u/lreal)\
**Post date:** [October 3, 2025, 9:10pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/7 "2025-10-03T21:10:52Z")

</div>

Any updates on that?

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 4, 2025, 7:54pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/8 "2025-10-04T19:54:14Z")

</div>

Not yet, I may investigate further tomorrow and be back with some more results if any

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 8, 2025, 10:34pm UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/9 "2025-10-08T22:34:09Z")

</div>

Hi @lreal I hope this sheds more light to your matter:

Deep Agents’ built‑in file system is a virtual FS stored in the graph state under `files`. Without a checkpointer you typically only see the final state (last write wins when sub‑agents write the same filename). With a checkpointer attached and streaming enabled, you can record every intermediate version of `improved_code.txt` during the single run.

Key points:

- **Virtual FS lives in state** : Deep Agents’ file tools (`write_file`, `read_file`, `ls`, `edit_file`) operate on a virtual FS backed by LangGraph state, not the host disk. See the built‑in components docs (File System Tools) and README.

- **Attach a checkpointer** : A checkpointer persists state snapshots at each step so you can retrieve the evolving `files` contents during a run.

- **Stream values to collect history** : While the graph runs, stream `values` and append each `files["improved_code.txt"]` snapshot to a list.

- **Optional on‑disk persistence** : Use a SQLite/Postgres checkpointer for durable history across processes; `InMemorySaver` suffices if you only need history for the current run.

```python
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import InMemorySaver
# Optional durable alternative:
# from langgraph.checkpoint.sqlite import SqliteSaver

# Build your agent exactly as you already do ...
# judge_agent = create_deep_agent(...)

# 1) Attach a checkpointer
checkpointer = InMemorySaver()
# For durability across sessions, prefer:
# checkpointer = SqliteSaver.from_conn_string("sqlite:///deep_agent_history.db")
judge_agent.checkpointer = checkpointer

# 2) Use a stable thread_id to keep the run’s history together
config = {"configurable": {"thread_id": "code-improver-1"}}

# 3) Stream the run and record each intermediate filesystem snapshot
history = [] # will hold all versions of improved_code.txt
for snapshot in judge_agent.stream(
    {"messages": [{"role": "user", "content": "Start the code improvement process."}]},
    config=config,
    stream_mode="values",
):
    files = snapshot.get("files", {})
    if "improved_code.txt" in files:
        history.append(files["improved_code.txt"]) # append each version

# 4) Optionally, also get the final aggregated result
final_result = judge_agent.invoke(
    {"messages": [{"role": "user", "content": "Summarize the final decision."}]},
    config=config,
)

# Now `history` contains every intermediate version the sub‑agents wrote,
# and `final_result.get("files", {}).get("improved_code.txt")` is the last version.

```

- When both sub‑agents write the same filename, the virtual FS reflects the latest write at that step. The checkpointer + streaming pattern above preserves the sequence of writes so you don’t lose intermediate versions.

- If you prefer to avoid last‑write‑wins entirely, give each sub‑agent a distinct filename (e.g., `improved_code.optimized.txt` and `improved_code.readable.txt`) and let the supervisor write the final merged output to `improved_code.txt`.

References:

- Deep Agents repository (README explains virtual FS, sub‑agents, and checkpointer usage): [langchain-ai/deepagents](https://github.com/langchain-ai/deepagents)
- Deep Agents overview: [docs.langchain.com/labs/deep-agents/overview](https://docs.langchain.com/labs/deep-agents/overview)
- Built‑in components — File System Tools: [docs.langchain.com/labs/deep-agents/built-in-components#file-system-tools](https://docs.langchain.com/labs/deep-agents/built-in-components#file-system-tools)
- Memory concepts (background on state/memory): [docs.langchain.com/oss/python/concepts/memory](https://docs.langchain.com/oss/python/concepts/memory)

---

<div class="post-metadata">

**Author:** ![lreal](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/lreal/32/1158_2.png) [@lreal](https://forum.langchain.com/u/lreal)\
**Post date:** [October 10, 2025, 9:23am UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/10 "2025-10-10T09:23:31Z")

</div>

That was helpful, thanks.

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 10, 2025, 10:44am UTC](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720/11 "2025-10-10T10:44:13Z")

</div>

Hi @lreal

I am happy it helped 😟