Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai
Python agentsagentskillscitationsclaude-codecodexcodex-plugincodex-skilldeep-researchdeep-research-agentdeepresearchmcp-serverresearchresearch-agentresearch-tools
Update CONTRIBUTING.md for the hyperresearch rename (#90)
Marcelo Oliveira108a3f71ba3f
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex ea4a219..f4b1de7 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -1,12 +1,12 @@-# Contributing to kasten+# Contributing to hyperresearchThank you for your interest in contributing.## Development setup```bash-git clone https://github.com/jordan-gibbs/kasten.git-cd kasten+git clone https://github.com/jordan-gibbs/hyperresearch.git+cd hyperresearchpython -m venv .venvsource .venv/bin/activate # or .venv\Scripts\activate on Windowspip install -e ".[dev]"@@ -18,15 +18,14 @@ pip install -e ".[dev]"python -m pytest tests/ -v```-All tests must pass before submitting a PR. The test suite runs in under 30 seconds.+All tests must pass before submitting a PR. The full suite takes a minute or two; run a single file while iterating.## Code styleThis project uses [ruff](https://docs.astral.sh/ruff/) for linting:```bash-ruff check src/-ruff format src/+ruff check src/ tests/```Configuration is in `pyproject.toml`. Line length is 100 characters.@@ -34,7 +33,7 @@ Configuration is in `pyproject.toml`. Line length is 100 characters.## Type checking```bash-mypy src/kasten/+mypy src/hyperresearch/```Strict mode is enabled in `pyproject.toml`.@@ -44,33 +43,34 @@ Strict mode is enabled in `pyproject.toml`.1. Fork the repository.2. Create a branch from `main`.3. Make your changes with tests.-4. Run `ruff check src/` and `python -m pytest tests/`.+4. Run `ruff check src/ tests/` and `python -m pytest tests/`.5. Open a pull request against `main`.Keep PRs focused on a single change. Include a clear description of what changed and why.## Reporting issues-Open an issue at [github.com/jordan-gibbs/kasten/issues](https://github.com/jordan-gibbs/kasten/issues). Include:+Open an issue at [github.com/jordan-gibbs/hyperresearch/issues](https://github.com/jordan-gibbs/hyperresearch/issues). Include:- What you expected to happen- What actually happened- Steps to reproduce-- kasten version (`kasten --version`)+- hyperresearch version (`hyperresearch --version`)- Python version and OS## Architecture overview-- `src/kasten/core/` -- vault management, sync engine, frontmatter parsing, SQLite schema-- `src/kasten/cli/` -- typer CLI commands, output formatting-- `src/kasten/search/` -- FTS5 search engine, filters, ranking-- `src/kasten/models/` -- Pydantic models for notes, output envelopes-- `src/kasten/graph/` -- link parsing (shared patterns)-- `src/kasten/indexgen/` -- auto-generated index page builder-- `src/kasten/ingest/` -- file, web, PDF ingestion-- `src/kasten/compile/` -- LLM compilation pipeline-- `src/kasten/llm/` -- provider abstraction (OpenAI, Anthropic, Ollama)-- `src/kasten/serve/` -- lightweight web UI server+- `src/hyperresearch/core/` -- vault management, sync engine, frontmatter parsing, SQLite schema+- `src/hyperresearch/cli/` -- typer CLI commands, output formatting+- `src/hyperresearch/search/` -- FTS5 search engine, filters, ranking+- `src/hyperresearch/models/` -- Pydantic models for notes, output envelopes+- `src/hyperresearch/graph/` -- link parsing (shared patterns)+- `src/hyperresearch/indexgen/` -- auto-generated index page builder+- `src/hyperresearch/web/` -- pluggable web providers (fetch and search backends)+- `src/hyperresearch/export/` -- export formatters+- `src/hyperresearch/mcp/` -- MCP server exposing research-base tools to agents+- `src/hyperresearch/skills/` -- bundled research skills installed into the harness+- `src/hyperresearch/serve/` -- lightweight web UI server- `tests/` -- pytest test suite-The key design principle: markdown files are the source of truth, SQLite is a derived cache that can be rebuilt at any time with `kasten sync --force`.+The key design principle: markdown files are the source of truth, SQLite is a derived cache that can be rebuilt at any time with `hyperresearch sync --force`.