DeepParallel
A multi-model agentic coding CLI with cross-model Guardian review. Many models check the work; you ship with a second opinion. Served via Crowe Logic.
Install
uv tool install deepparallel # recommended
# or
pipx install deepparallel --python python3.13
Then run deepparallel (or the short alias dp).
Note: on systems with a broken Homebrew Python 3.14, bare pipx install may
fail to find a usable interpreter - use uv tool install or pin --python.
From source
uv venv
uv pip install -p .venv -e .
Configure
Free is bring-your-own-key, and the backend is auto-detected from whatever
credentials the machine already has (a .env file in the working directory is
loaded automatically). Detection order: Azure creds, then an OpenAI key, then
an OpenAI-compatible endpoint, then a local Ollama. With none of these, dp
prints setup guidance instead of starting.
# OpenAI
OPENAI_API_KEY=sk-...
# Local Ollama: install from https://ollama.com and start it - no other
# config needed; the first installed model is used unless
# DEEPPARALLEL_MODEL is set.
# Any OpenAI-compatible endpoint (incl. the Crowe Logic Foundry control plane)
FOUNDRY_BASE_URL=https://<control-plane>
FOUNDRY_API_KEY=<token>
# Azure OpenAI
AZURE_CORE_ENDPOINT=https://<resource>.openai.azure.com
AZURE_CORE_API_KEY=<key>
DEEPPARALLEL_API_VERSION=2024-08-01-preview # optional
Pin a backend explicitly with DEEPPARALLEL_BACKEND=openai|ollama|foundry|azure|crowe
(or [backend] backend = "..." in ~/.config/deepparallel/config.toml).
Use
deepparallel # interactive agent chat
deepparallel run "question" # one-shot, pipe-friendly (answer on stdout)
deepparallel tools # list the agent's tools
deepparallel info # model + backend status
deepparallel doctor # diagnose config + reachability
deepparallel run --no-tools "..." # plain chat, no tools
deepparallel run --yes "..." # auto-approve tool actions
deepparallel review <file|--diff> # cross-model review as a CI gate (Pro)
deepparallel audit <file> # supply-chain gate: catch hallucinated deps (Pro)
deepparallel research conduit # latent-relay research demo (needs [research] extra)
Supply-chain gate
LLMs invent package names that don't exist — and attackers register those names
("slopsquatting"). deepparallel audit <file> extracts the dependencies a file
introduces (imports, requirements.txt, package.json) and checks each against the
real registry (PyPI / npm), flagging any the registry has never seen. Exit 0
clean, 2 if a likely-hallucinated package is found — so it gates a commit or PR.
The Guardian also runs this automatically on every edit: a hallucinated import
forces a confirmation even under --yes.
Fusion (stacking models for stronger output)
deepparallel can stack the answerer with a separate reasoning model. All modes
compose hosted backends (no GPU/weight-merging), so they are API-call stacking.
deepparallel run --fuse reason "hard question" # reasoner thinks, answerer answers
deepparallel run --fuse escalate "question" # answer first; escalate to reasoner only if unsure
deepparallel run --deep "question" # heavy: many models in parallel + a judge (slow)
deepparallel run --dual "A,B" "question" # compare two deployments side by side
deepparallel run --dual "A,B" --synth "question" # ...and synthesize a merged answer
--fuse also works in interactive chat. Set a default with DEEPPARALLEL_FUSION=reason.
Fusion-native UX (what single-model agents cannot do)
- Guardian review - before an edit (
write_file/edit_file/ast_replace_symbol) is applied, a second model reviews the diff and its verdict (safe/risky: .../bug: ...) is shown in the confirm card. Advisory: you still approve. Toggle withDEEPPARALLEL_GUARDIAN; pick the reviewer withDEEPPARALLEL_GUARDIAN_DEPLOYMENT. - Consensus + divergence -
run --deepprints aconsensus:chip from cross-model agreement (agreement, not correctness), and on low agreement lists the dissenting candidates. - Live dial - in interactive chat,
/fast,/fuse,/escalateswitch the fusion mode mid-session (shown in the prompt);/deepruns the next prompt as a multi-model query.
Agent and tools
deepparallel is an agent: it can call tools to inspect and change your project.
- Read-only (run automatically):
read_file,list_dir,glob,grep,ast_symbols,ast_show_symbol,web_fetch,web_search,analyze_image. - Mutating / executing (require confirmation):
write_file,edit_file,ast_replace_symbol,run_shell,run_code,open_path(open a file, folder, or URL in the OS default app - e.g. an HTML report in the browser).
In interactive chat, type /auto to toggle auto-approve (tools run without
asking; edits outside the project and unknown dependencies still confirm), or
start with deepparallel --yes.
web_search needs DEEPPARALLEL_SEARCH_API_KEY; analyze_image works out of the
box on a multimodal deployment (override with DEEPPARALLEL_VISION_DEPLOYMENT).
In interactive chat, mutating actions prompt for y/n. In run (non-interactive)
they are denied unless you pass --yes. ast_* tools are multi-language via
tree-sitter; run_code executes in a Docker sandbox when available, else a
timeboxed local subprocess.
Configuration reference
| Variable | Purpose | Default |
|---|---|---|
DEEPPARALLEL_BACKEND |
azure or foundry |
azure |
AZURE_CORE_ENDPOINT / AZURE_CORE_API_KEY |
Azure transport | (required for azure) |
AZURE_MIKE9320_ENDPOINT / AZURE_MIKE9320_KEY, AZURE_MIKE6250_ENDPOINT / AZURE_MIKE6250_KEY |
the other Azure resources in models.json; a model id resolves to every resource that is keyed |
(optional; unlocks Claude, GPT-5.6, Kimi K3) |
DEEPPARALLEL_API_VERSION |
Azure API version | 2024-08-01-preview |
FOUNDRY_BASE_URL / FOUNDRY_API_KEY |
control-plane transport | (required for foundry) |
DEEPPARALLEL_TEMPERATURE |
default sampling temperature | 0.4 |
DEEPPARALLEL_MAX_TOKENS |
response cap (large enough to write whole files) | 8192 |
DEEPPARALLEL_THINK |
surface reasoning stream | 0 (answer-only) |
DEEPPARALLEL_TOOLS |
enable agent tools | 1 (on) |
DEEPPARALLEL_AUTO_APPROVE |
auto-approve mutating tools | 0 (off) |
DEEPPARALLEL_MAX_STEPS |
max agent tool-call rounds | 12 |
DEEPPARALLEL_SHELL_TIMEOUT |
run_shell timeout (s) | 120 |
DEEPPARALLEL_SANDBOX |
auto / docker / subprocess for run_code |
auto |
DEEPPARALLEL_PLAIN |
force plain (non-rich) output | 0 |
DEEPPARALLEL_FUSION |
default fusion: off / reason / escalate |
off |
DEEPPARALLEL_REASONER_DEPLOYMENT |
reasoner model for fusion | gpt-5.6 |
DEEPPARALLEL_PARALLEL_MODELS |
comma-separated chains for --deep |
gpt-5.6,claude-fable-5-1,DeepSeek-V4-Pro,grok-4.3,Kimi-K3 |
DEEPPARALLEL_JUDGE_DEPLOYMENT |
judge/synthesizer model | gpt-5.6 |
DEEPPARALLEL_SEARCH_API_KEY |
enables web_search (Brave Search API) | (unset) |
DEEPPARALLEL_SEARCH_URL |
search API endpoint | Brave web search |
DEEPPARALLEL_VISION_DEPLOYMENT |
multimodal model for analyze_image | Llama-4-Scout |
DEEPPARALLEL_GUARDIAN |
second-model review of edits before apply | 1 (on) |
DEEPPARALLEL_GUARDIAN_DEPLOYMENT |
the reviewer model | DeepSeek-V4-Flash |
DeepParallel is served via Crowe Logic infrastructure. https://crowelogic.com
Metadata
Release files for deepparallel 0.11.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| deepparallel-0.11.3.tar.gz | 236.0 kB | Without provenance | Details for deepparallel-0.11.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| deepparallel-0.11.3-py3-none-any.whl | Python 3 | none | any | Details for deepparallel-0.11.3-py3-none-any.whl |
Total release size: 432.4 kB
Release files / deepparallel-0.11.3.tar.gz
| Download URL | deepparallel-0.11.3.tar.gz |
|---|---|
| Size | 236.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ad1cdfae82c4dca4041ef9bb7ed4838a916ba3af883413410cccb0e91c35f57e
|
|
BLAKE2b-256 checksum How to use checksums |
9bb1002f7f9ee52e6da67d7d428a1b4d2e85ddf9441b9cc10eb670683f6bd6cf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.23 {"installer":{"name":"uv","version":"0.11.23","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / deepparallel-0.11.3-py3-none-any.whl
| Download URL | deepparallel-0.11.3-py3-none-any.whl |
|---|---|
| Size | 196.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1d689946bfb9a119b19aa3c53fa6185a2741bf65d447d1b82ebfd95994468a55
|
|
BLAKE2b-256 checksum How to use checksums |
24daf13b580d3a0fdb2a212f25669ee15d8d6442d0e789df46fd34d50cfc572c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.23 {"installer":{"name":"uv","version":"0.11.23","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for deepparallel 0.11.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.