# 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:** 1\
**Showing post:** 9

<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)

---

_[View the full topic](https://forum.langchain.com/t/deep-agent-persistent-file-system/1720)._