processfork 1.0.8

fork() for AI agents — snapshot, branch, and merge live agent state.

ProcessFork

git for AI agents. Snapshot, fork, and merge live LLM sessions in 8 ms.

_{↑ Replay it locally: asciinema play demo/processfork-demo.cast}

---

Why

You're 4 hours into a refactor with Claude Code. The agent has read 200 files, run 47 tests, opened a database, started a dev server. Then it suggests a destructive change.

Today: lose everything, undo by hand, or restart. With ProcessFork: pf snapshot → 8 ms → safe. Try 12 alternatives in parallel, merge the winner back, ship the whole session to a teammate.

It's git — snapshot, branch, merge, push, clone — but for live AI agent state.

Highlights

• ⚡ 8 ms snapshots. Full agent state — model + KV-cache + files + tools + reasoning — into one content-addressed .pfimg.
• 🌳 Real fork & merge. 12 parallel attempts share storage automatically (CoW). Merge the winner with a real 3-way diff (files, tools, trace) — git-style <<<<<<< markers and all.
• 🔒 Won't double-send your email. HMAC-chained tool-call ledger; restored agents see prior side-effects as facts, not as actions to re-issue. (ACRFence-resistant.)
• 🤝 Drop-in for Claude Code, LangGraph, OpenInterpreter, vLLM, SGLang, AutoGen, CrewAI.
• 📦 Single binary, MIT, Rust core, Python + TypeScript SDKs. 200+ tests.

Quick start (60 seconds)

# install the CLI:
cargo install processfork                      # → `pf` on your $PATH

# snapshot a directory:
mkdir /tmp/sandbox && echo "fn main() {}" > /tmp/sandbox/main.rs
pf snapshot --agent-id demo --fs-root /tmp/sandbox
# → sha256:1c2497b0…   ⏱ 8 ms

# edit something, snapshot again, see the diff:
echo "fn main() { println!(\"hi\") }" > /tmp/sandbox/main.rs
pf snapshot --agent-id demo --fs-root /tmp/sandbox --name v2
pf log
pf diff <first-cid> <second-cid>

Prefer Python? pip install processfork. TypeScript? npm install @processfork/sdk.

The full 60-second demo (snapshot → fork ×12 → merge → push → clone on a fresh store) is bash demo/script.sh. Runs end-to-end on a laptop. No GPU, no API keys.

When you'd reach for it

Situation	Command
Agent about to do something destructive	pf snapshot pre-rm-rf
Stuck — want to try 12 approaches in parallel	pf fork -n 12 --explore "fix bug"
Hand a complex session to a teammate	pf push hf://you/session-name
Time-travel debug ("when did it go wrong?")	pf log then pf checkout <CID>
RL rollout fabric for agent training	snapshot, fan out, score, merge

Use it with your stack

Adapter	Status	What it gives you
Claude Code	✅ ships now	/snapshot, /fork, /merge slash-commands inside any session
LangGraph	✅ ships now	drop-in BaseCheckpointSaver (full 4-layer, not just state dict)
OpenInterpreter	✅ ships now	interpreter.snapshot("pre-rm-rf") then .checkout("pre-rm-rf")
AutoGen	✅ ships now	atomic snapshot across a whole agent group's state
CrewAI	✅ ships now	CrewMemory drop-in; every step time-travelable
vLLM	✅ ships now	bit-exact KV-cache snapshot/restore (V0 + V1 engine via collective_rpc)
SGLang	✅ ships now	live RadixCache k_buffer/v_buffer capture, mock-mode parity tests

How it works

ProcessFork captures the five things that together make up a live agent — atomically — into one content-addressed file:

Layer	What it captures
Model	LoRA / IA³ / full-finetune weight diffs, in-place TTT updates
Cache	Paged KV-cache, content-addressed per page (CoW across forks)
World	Filesystem, env, in-flight subprocesses, browser DOM
Effects	Append-only ledger of irreversible tool calls (HMAC-chained)
Trace	Chat + tool-call message log

Identical content shares storage automatically — 12 parallel forks use ~1.5× the space of one, not 12×. The merge engine handles each layer with the right algorithm: git-style 3-way diff for files, TIES + DARE for model weights, an HMAC chain that defends against semantic-rollback attacks (ACRFence), and an LLM-summarized "what branch B learned" patch injected into branch A's reasoning trace without re-prefilling the cache.

→ Architecture deep-dive · Three-way merge protocol · Engineering specs

Status

v1.0.8 tagged. Closes the 5th and final round-5 audit blocker: cargo-audit ignore list dropped from 5 IDs → 1 (and that one is a stylistic warning on a transitive progress-bar dep). Concretely: pyo3 0.22 → 0.24 retires RUSTSEC-2025-0020, and switching aws-config / aws-sdk-s3 from the legacy rustls feature to default-https-client retires RUSTSEC-2026-0098/0099/0104 (rustls 0.21 → 0.23, rustls-webpki 0.101 → 0.103). cargo deny check reports advisories ok, bans ok, licenses ok, sources ok. v1.0.7's other four round-5 fixes still apply: env capture redacts secret-shaped names by default; ledger writes go through real pf_effects::Ledger::append HMAC chaining + pf verify validates the chain; vLLM/SGLang plugins actually write K/V page bytes + manifest to the store and read them back on checkout; versions aligned across surfaces.

metric	observed	target
Snapshot p50, synthetic 4-layer fixture (macOS arm64)	7.9 ms	< 500 ms p99
Snapshot p50, real GPU host (Modal A10G, 64 × 4 KiB)	42 ms (warm)	< 500 ms p99
Bit-exact KV-cache replay, vLLM 0.6.6 + TinyLlama-1.1B on A10G	✅ verified — 38 619 KV pages snapshotted, restored, regenerated text byte-identical	out_a == out_b
Cache capture, 64 pages	531 µs	—
12-fork ÷ 1-fork storage ratio	well < 1.5×	≤ 1.5×
Total tests passing	200	—

Synthetic-fixture numbers come from cargo bench --workspace. GPU numbers come from modal run scripts/gpu-validate-modal.py; raw JSON lives in benchmarks/gpu-validation/ and the breakdown in benchmarks/RESULTS.md. vLLM ≥0.10 (V1 engine, subprocess-worker architecture) is the v1.0.2 milestone — the v1.0.1 adapter targets V0's directly-introspectable CacheEngine.

Install

cargo install processfork                          # Rust CLI (the `pf` binary)
pip   install processfork                          # Python SDK
npm   install @processfork/sdk                     # TypeScript SDK

Per-adapter packages (one each on PyPI):

pip install processfork-claude-code
pip install processfork-langgraph
pip install processfork-openinterpreter
pip install "processfork-vllm[vllm]"               # needs CUDA + vllm ≥ 0.10
pip install "processfork-sglang[sglang]"           # needs CUDA + sglang ≥ 0.5
pip install "processfork-autogen[autogen]"
pip install "processfork-crewai[crewai]"

Build from source if you want to hack on it:

git clone https://github.com/manav8498/processfork && cd processfork
cargo build --release -p processfork               # → target/release/pf

Full build-from-source instructions in docs/install.md. Pre-built wheels cover macOS arm64, Linux x86_64, and Linux aarch64; macOS Intel + Windows wheels arrive in v1.0.1 (operator: same package, just more platforms).

Repo layout

crates/      Rust workspace (10 crates: pf-core, pf-cache, pf-world, pf-effects,
             pf-model, pf-merge, pf-registry, processfork (CLI, the `pf` binary), pf-py, pf-ts)
adapters/    7 first-party integration packages
benchmarks/  PFBench harness + Criterion microbench
docs/        mdBook source (25+ pages)
examples/    8 self-contained runnable examples
demo/        60-second demo recording script

Docs

Your first fork (5 min) · 60-second demo · Architecture · Merge protocol · Security model · Performance tuning · Engineering specs

Contributing

PRs welcome. The bar is cargo fmt, cargo clippy --all-targets -- -D warnings, cargo test --workspace, plus a green coverage delta. See CONTRIBUTING.md.

License

MIT.