Development
Plugin
bitloops
Give AI coding agents the context they need to ship production-quality software.
Plugin Signal59/100Fair
maintained66
capable29
documented100
adopted50
Install
$ npx -y skills add bitloops/bitloops --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Stats
235
Stars
17
Forks
Maintained
Maintenance
Rust
Language
Apache-2.0
License
2mo ago
Last commit
5mo ago
Created
Repo: bitloops/bitloops
In this plugin
See everything inside What's inside
Skills
2/devql-explore-firstUse always before codebase exploration, bug fixing, SWE-bench tasks, locating symbols, files, or tests, or before using rg, grep, sed, find, or source-file reads in a repository./using-devqlUse when answering repo-understanding questions in a Bitloops repo with DevQL guidance enabled, especially when you need to locate code by path, line range, exact symbol, or approximate/conceptual search before reading files.
README
1
Quick Start
Fast scripted setup installs Bitloops and applies the default daemon config:
macOS, Linux, WSL:
curl -fsSL https://bitloops.com/install.sh | bash -s -- --default-config
Windows PowerShell:
& ([scriptblock]::Create((irm https://bitloops.com/install.ps1))) -DefaultConfig
Then, from inside the repo you want Bitloops to capture:
bitloops init
Prefer to configure manually? Install without the default-config flag, then run:
bitloops configure --web
bitloops init
Work normally with Codex, Claude Code, Cursor, Gemini, Opencode or Copilot. Commit as usual. Bitloops captures the relevant context around every change and keeps your codebase model fresh in the background.
Open the local dashboard:
bitloops dashboard
Other install paths and full setup → Docs
What You Get
- 🧠 Persistent codebase substrate — files, symbols, dependencies, tests, and history modeled as a queryable graph, not text.
- 🪶 Automatic context capture — decisions, constraints, and reasoning are pulled from your agent conversations as you work. No markdown file to maintain.
- 🎯 Relevance-ranked retrieval — every prompt gets the artifacts that actually matter. Not all files. Not random files. The right ones.
- 🔁 Cross-agent memory — what you decided in Claude Code yesterday guides Cursor today and Copilot tomorrow. Same substrate underneath all of them.
- 🧾 Provenance from commit to prompt — every commit traces back to the prompt, model, and rejected alternatives that produced it. Two weeks later you can still answer "why."
- 🗺️ Code City spatial view — a live map of your codebase. Files as buildings, height as size, arcs as dependencies. Filter by what AI touched.
- 🔍 DevQL — a typed query language for your codebase model. Ask precise questions instead of grepping.
- 🔒 Local-first — your code isn't stored on our infrastructure. The daemon runs on your machine.
- 🧩 Drops in alongside your agent — no agent switch, no IDE switch. Bitloops is the substrate underneath.
Why Bitloops Exists
You've already built the workaround. A CLAUDE.md that grew to 2,000 lines. A .cursor/rules folder you copy-paste between projects. An AGENTS.md you swear you'll keep updated. A shell script that concatenates the "right" files into every prompt.
The pattern is always the same: a second brain for your codebase, built in markdown, manually maintained, going stale every week.
AI coding agents are bottlenecked by state, not generation. A codebase isn't fundamentally text — it's a system of files, symbols, APIs, tests, decisions, and history. Most agents force that structured system through an unstructured medium (prompt text, RAG chunks, embeddings) and have to infer the system over and over.
The loop today:
retrieve → infer → act → forget
Bitloops changes the loop to:
capture → persist → rank → serve → refresh
Agents can't reliably change systems they can't model. Bitloops builds and maintains the model.
The Old Way vs The Bitloops Way
| You're doing this today | With Bitloops |
|---|---|
| Re-explaining your architecture every session | Substrate captured once. Re-served on every prompt. |
Hand-writing CLAUDE.md / .cursor/rules / AGENTS.md | Decisions and constraints captured automatically from your agent conversations. |
| Agent re-implements a util that already exists three folders over | Static analysis + clone detection feeds existing code into pre-edit context. |
| "Why is this here?" → the prompt is gone | Commit → prompt → rejected alternatives, all traceable. |
| Five rules files for five agents | One substrate. Claude Code, Cursor, Copilot — same model underneath. |
| RAG embeddings rebuilt every session | Long-lived daemon. Index is always-on, always-current. |
| Repository uploaded and stored on a vendor's infra | Runs locally. Code processed, not stored. |
How It Works
┌──────────────────────────────────────────────────────────────────────┐
│ Your agent (Claude Code / Cursor / Copilot) makes a request │
└──────────────────────────────────────────────────────────────────────┘
↓
┌──────────────────────────────────────────────────────────────────────┐
│ Bitloops hooks capture the prompt, transcript, and tool events │
└──────────────────────────────────────────────────────────────────────┘
↓
┌──────────────────────────────────────────────────────────────────────┐
│ Local daemon updates the codebase graph (files, symbols, deps) │
└──────────────────────────────────────────────────────────────────────┘
↓
┌──────────────────────────────────────────────────────────────────────┐
│ DevQL ranks and serves the right artifacts back into the agent │
└──────────────────────────────────────────────────────────────────────┘
↓
┌──────────────────────────────────────────────────────────────────────┐
│ Commit links to the prompt, model, and decision that produced it │
└──────────────────────────────────────────────────────────────────────┘
Architecture deep-dive → Docs › Architecture
Who Bitloops Is For
- Devs shipping multiple AI-assisted PRs per week with Claude Code, Cursor, Copilot, or Codex — who've stopped being amazed and started being annoyed.
- Anyone maintaining a CLAUDE.md,
.cursor/rules, or AGENTS.md and quietly knowing it's already out of date. - Engineering teams who want a reviewable trail for AI-assisted work — prompts, tool events, decisions, commits — not just diffs.
- Platform and DevEx teams building internal AI workflows who need a typed local substrate for agent context.
Supported Agents & Languages
Agents:
- Claude Code
- Codex
- Cursor
- Gemini
- Copilot
- OpenCode
Languages:
- Rust
- TypeScript / JavaScript
- Python
- Go
- Java
- C#
- PHP
- C++
Local-First Trust Model
Your code isn't stored on our infrastructure. The daemon runs on your machine; configuration, repository model, event data, and blobs stay local by default.
LLM reasoning over commits, code, and conversations is part of the system — that processing requires sending content to a model provider, and an account is required to authenticate it. The line: your code isn't stored, it is processed.
Demo video
Documentation
- 📖 Quickstart — set up and first capture
- 🔍 DevQL — query the codebase model
- 🏗️ Docs home — guides, concepts, troubleshooting
- 🛠️ Contributing — rules, dev setup, extension guides
Community
- 💬 GitHub Discussions — questions, ideas, feedback
- 🐛 Issues — bug reports, feature requests
- 🔒 Security — responsible disclosure
- 🤝 Code of Conduct If Bitloops is solving a problem you've felt — star the repo. It tells us we're building the right thing, and it tells other devs the project is real.
License
Apache-2.0. See LICENSE.
File tree
1723bitloops/bitloopsView on GitHub
.bitloopsignore
.cargo/
config.toml
.config/
nextest.toml
.github/
scripts/
documentation-consistency-ai-review.mjs
rust-standards-ai-review.mjs
workflows/
allow-main-only-via-develop.yml
changelog-check.yml
ci.yml
dev-ci.yml
develop-coverage-baseline.yml
develop-qat.yml
documentation-consistency-ai.yml
release.yml
rust-standards-ai.yml
.gitignore
.vscode/
launch.json
rust.code-profile
settings.json
tasks.json
AGENTS.md
assets/
bitloops_getting_started.png
bitloops-logo_320x132.png
bitloops/
bitloops-inference-protocol/
Cargo.toml
src/
lib.rs
.cargo/
config.toml
.coverage-baseline.jsonl
.gitignore
build.rs
Cargo.lock
Cargo.toml
config/
dashboard_urls.json
dashboard_urls.template.json
examples/
export-dashboard-schema.rs
export-schema.rs
export-slim-schema.rs
qat/
features/
agents-checkpoints/
agents_checkpoints.feature
devql/
devql-ingest/
ingest_workspace.feature
devql-sync/
sync_workspace.feature
agent_enablement_queryable.feature
architecture_graph.feature
architecture_roles.feature
blast_radius_temporal.feature
context_guidance_smoke.feature
cross_capability_smoke.feature
knowledge_ingestion.feature
semantic_clones.feature
test_harness_proof_map.feature
onboarding/
onboarding.feature
smoke/
agent_cli_smoke.feature
checkpoint_timeline_smoke.feature
README.md
RUN.md
schema.dashboard.graphql
schema.graphql
schema.slim.graphql
scripts/
coverage-baseline-check.sh
qa/
semantic_clones_ann_ab.sh
test-coverage.sh
test-summary.sh
src/
adapters/
adapters.rs
agents/
agents.rs
adapters/
adapters_test/
adapters_test.rs
builtin_tests.rs
fixtures.rs
registry_tests.rs
adapters.rs
builtin.rs
registration.rs
registry.rs
types/
types.rs
compatibility.rs
config.rs
descriptor.rs
package.rs
readiness.rs
util.rs
agent_test.rs
canonical/
canonical.rs
compatibility.rs
identity.rs
invocation.rs
lifecycle.rs
progress.rs
result.rs
stream.rs
tests.rs
chunking_test.rs
chunking.rs
claude_code/
claude_code.rs
agent.rs
git_hooks_tests.rs
git_hooks.rs
hooks_cmd.rs
hooks.rs
skills.rs
transcript/
transcript.rs
lines.rs
message_types.rs
subagents.rs
tests/
tests.rs
parsing.rs
subagents.rs
token_usage.rs
tool_events.rs
token_usage.rs
tool_events.rs
codex/
codex.rs
agent_tests.rs
agent.rs
config_tests.rs
config.rs
hooks_cmd.rs
hooks_tests.rs
hooks.rs
lifecycle_tests.rs
lifecycle.rs
skills.rs
transcript.rs
types.rs
copilot/
copilot.rs
agent.rs
hooks.rs
lifecycle.rs
skills.rs
transcript.rs
types.rs
cursor/
cursor.rs
agent.rs
hooks_cmd.rs
hooks.rs
lifecycle.rs
rules.rs
transcript.rs
types.rs
FAMILY_PROFILE_PLAYBOOK.md
gemini/
gemini.rs
agent/
agent_tests.rs
agent.rs
analysis.rs
cli_agent.rs
config.rs
hooks.rs
time.rs
lifecycle.rs
skills_integration_tests.rs
skills.rs
transcript_tests.rs
transcript.rs
open_code/
open_code.rs
agent_api.rs
agent_hook_support.rs
agent_runtime.rs
agent_session_io.rs
cli_commands.rs
hooks.rs
open_code_agent_tests.rs
plugin.rs
skills.rs
transcript.rs
types.rs
policy.rs
registry_test.rs
registry.rs
session_test.rs
session.rs
skill_install.rs
types.rs
connectors/
connectors.rs
confluence.rs
github.rs
jira.rs
registry.rs
types.rs
languages/
languages.rs
cpp/
cpp.rs
canonical.rs
edges.rs
extraction.rs
pack.rs
test_support.rs
csharp/
canonical.rs
edges.rs
extraction.rs
mod.rs
pack.rs
test_support.rs
go/
go.rs
canonical.rs
edges.rs
extraction.rs
pack.rs
test_support.rs
java/
java.rs
canonical.rs
edges/
edges.rs
calls.rs
imports.rs
references.rs
relationships.rs
support.rs
tests.rs
extraction.rs
pack.rs
test_support.rs
php/
php.rs
canonical.rs
edges.rs
extraction.rs
pack.rs
test_support.rs
python/
python.rs
canonical.rs
edges.rs
extraction.rs
pack.rs
test_support.rs
rust/
rust.rs
canonical.rs
edges.rs
extraction.rs
http_facts.rs
pack.rs
test_support/
test_support.rs
attributes.rs
doctests.rs
enumeration.rs
imports.rs
macros.rs
matching.rs
rstest.rs
scenarios.rs
ts_js/
ts_js.rs
canonical.rs
edges.rs
extraction.rs
pack.rs
test_support.rs
model_providers/
model_providers.rs
llm/
llm.rs
chat_completions_http.rs
api/
api.rs
bundle_types.rs
bundle.rs
dashboard_fallback_install.html
dashboard_file_diffs.rs
dashboard_git.rs
dashboard_params.rs
dashboard_paths.rs
dashboard_runtime.rs
dashboard_schema.rs
dashboard_service/
dashboard_service.rs
analytics.rs
bundle.rs
checkpoint.rs
graphql.rs
interaction.rs
queries.rs
repository.rs
dashboard_types.rs
db/
db.rs
clickhouse.rs
config.rs
duckdb.rs
health.rs
init.rs
pools.rs
postgres.rs
sqlite.rs
tests.rs
error.rs
handlers/
handlers.rs
git_blob.rs
repo.rs
router.rs
runtime_schema/
runtime_schema.rs
capability_packs/
capability_packs.rs
catalog.rs
fields.rs
models.rs
operations.rs
patches.rs
review.rs
sections.rs
selection.rs
tests.rs
values.rs
config_management/
config_management.rs
errors.rs
identity.rs
patch.rs
persistence.rs
redaction.rs
sections.rs
snapshot.rs
targets.rs
types.rs
validation.rs
config.rs
debug.rs
events.rs
executables.rs
handlers.rs
init_session.rs
roots.rs
schema.rs
snapshot.rs
start_init.rs
util.rs
watchers.rs
tests/
tests.rs
dashboard_api_bundle.rs
dashboard_config_utils.rs
devql_knowledge_clone_events.rs
devql_mutations_and_health.rs
devql_repository_graph/
devql_repository_graph.rs
artefacts.rs
commits.rs
loaders.rs
projects.rs
devql_routes_subscriptions.rs
numstat_output.rs
support_api_harness.rs
support_dashboard.rs
support_graphql_history.rs
support_graphql_knowledge.rs
support_graphql_monorepo.rs
support_storage.rs
tls.rs
artefact_query_planner.rs
capability_packs/
capability_packs.rs
architecture_graph/
architecture_graph.rs
current_state/
current_state.rs
builder.rs
consumer.rs
entry_points/
... 1600 moreShowing a partial view of a very large repo.
FAQ
bitloops is a Claude Code plugin with 2 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes devql-explore-first, using-devql. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is bitloops?
- Give AI coding agents the context they need to ship production-quality software.
- How do I install bitloops?
- Run these in Claude Code: npx -y skills add bitloops/bitloops --agent claude-code. Then prompt normally.
- Does bitloops auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is bitloops free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.