A network of agentic research specialists coordinated by a principal investigator agent. V1: web-search researcher MCP server + CLI shim.
Find a file
Jeff Smith d0a732735e Propagate parent env to MCP server subprocess (#18)
The mcp SDK's StdioServerParameters does not pass the parent
process's environment to the spawned server by default, so env
vars set on the CLI process (notably MARCHWARDEN_MODEL) were
silently dropped on the way to the researcher.

Pass env=os.environ.copy() to StdioServerParameters so the server
sees the same environment as the CLI. Also update scripts/docker-test.sh
to forward MARCHWARDEN_MODEL into the container and to detect a
non-TTY parent so non-interactive `ask` invocations don't fail with
"the input device is not a TTY".

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 15:31:14 -06:00
cli Propagate parent env to MCP server subprocess (#18) 2026-04-08 15:31:14 -06:00
orchestrator Initial project structure and scaffolding 2026-04-08 11:57:15 -06:00
researchers Enforce token_budget before each iteration (#17) 2026-04-08 15:29:22 -06:00
scripts Propagate parent env to MCP server subprocess (#18) 2026-04-08 15:31:14 -06:00
tests M2.2: marchwarden replay CLI command (#9) 2026-04-08 14:57:37 -06:00
.dockerignore chore: add docker-based test environment (#13) 2026-04-08 15:06:12 -06:00
.gitignore Initial project structure and scaffolding 2026-04-08 11:57:15 -06:00
CLAUDE.md chore: add CLAUDE.md for session 1 2026-04-08 14:44:16 -06:00
CONTRIBUTING.md Initial project structure and scaffolding 2026-04-08 11:57:15 -06:00
Dockerfile chore: add docker-based test environment (#13) 2026-04-08 15:06:12 -06:00
pyproject.toml chore: add docker-based test environment (#13) 2026-04-08 15:06:12 -06:00
README.md chore: add docker-based test environment (#13) 2026-04-08 15:06:12 -06:00

Marchwarden

A network of agentic research specialists coordinated by a principal investigator agent.

Marchwarden researchers are stationed at the frontier of knowledge — they watch, search, synthesize, and report back what they find. Each specialist is self-contained, fault-tolerant, and exposed via MCP. The PI agent orchestrates them to answer complex, multi-domain questions.

V1: Single web-search researcher + CLI shim for development.
V2+: Multiple specialists (arxiv, database, internal docs, etc.) + PI orchestrator.

Quick start

# Clone
git clone https://forgejo.labbity.unbiasedgeek.com/archeious/marchwarden.git
cd marchwarden

# Install
pip install -e .

# Ask a question
marchwarden ask "What are ideal crops for a garden in Utah?"

# Replay a research session
marchwarden replay <trace_id>

Docker test environment

A reproducible container is available for running the test suite and the CLI without depending on the host's Python install:

scripts/docker-test.sh build           # build the image
scripts/docker-test.sh test             # run pytest
scripts/docker-test.sh ask "question"   # run `marchwarden ask` end-to-end
                                        # (mounts ~/secrets ro and ~/.marchwarden rw)
scripts/docker-test.sh replay <id>      # replay a trace from ~/.marchwarden/traces
scripts/docker-test.sh shell            # interactive bash in the container

Documentation

Status

  • V1 scope: Issue #1
  • Branch: main (development)
  • Tests: pytest tests/

Stack

License

(TBD)