hivemind-ai 1.9.0

Orchestrate distributed swarms of AI agents that collaboratively solve complex tasks.

Hivemind

Distributed AI Swarm Runtime

Orchestrate multi-agent systems with a swarm execution model: tasks → DAG → parallel execution.

Install: PyPI package hivemind-ai · CLI hivemind

---

Quick start

1. Install (Python 3.12+):

pip install hivemind-ai
# or: uv add hivemind-ai

2. Set up API keys (pick one):

Store credentials in your OS keychain so you never re-enter them:

hivemind credentials set openai api_key      # prompts for value
hivemind credentials set anthropic api_key
hivemind credentials set github token
# or migrate from .env:
hivemind credentials migrate

Or use environment variables: OPENAI_API_KEY, ANTHROPIC_API_KEY, GITHUB_TOKEN, etc. (see Credentials).

3. Create a project and run:

hivemind init
hivemind run "Summarize swarm intelligence in one paragraph."

4. Optional — shell completion:

# Bash: add to ~/.bashrc
eval "$(hivemind completion bash)"

# Zsh: add to ~/.zshrc
eval "$(hivemind completion zsh)"

---

Run from code

From config file:

from hivemind import Swarm

swarm = Swarm(config="hivemind.toml")
results = swarm.run("Analyze diffusion models and write a one-page summary.")

Explicit parameters:

from hivemind import Swarm

swarm = Swarm(worker_count=4, worker_model="gpt-4o-mini", planner_model="gpt-4o-mini", use_tools=True)
results = swarm.run("Your task here.")

Credentials are injected from the keyring (or env) when config is resolved—no code changes needed.

---

Credentials

API keys are not stored in config files. Use the credential store (OS keychain) or environment variables.

What you want	Command or method
Store a key securely	hivemind credentials set <provider> <key> (prompts; uses keyring)
List stored keys (no values)	hivemind credentials list
Import from .env / TOML	hivemind credentials migrate
Export for sourcing / .env	hivemind credentials export <provider> → prints KEY=value lines
Remove a key	hivemind credentials delete <provider> <key>

Providers: openai, anthropic, github, gemini, azure, azure_anthropic (keys: api_key, token, endpoint, deployment, api_version as applicable).

Example — export and source in a script:

eval "$(hivemind credentials export azure)"
hivemind run "Your task"

See Configuration and CLI for details.

---

CLI

Command	Description
hivemind init	Set up a new project (hivemind.toml)
hivemind doctor	Check environment (keys, config, tools)
hivemind run "task"	Run swarm on a task
hivemind tui	Terminal UI (prompt, dashboard, logs)
hivemind credentials set/list/migrate/export/delete	Manage API keys (keyring)
hivemind completion bash | zsh	Print shell completion script
hivemind research [path]	Literature review on a directory
hivemind analyze [path]	Analyze repository architecture
hivemind memory [--limit N]	List memory entries
hivemind query "…"	Query knowledge graph
hivemind workflow <name>	Run a workflow from workflow.hivemind.toml
hivemind graph [run_id]	Export task DAG as Mermaid
hivemind replay [run_id]	Replay a run from event log
hivemind cache stats | clear	Task result cache
hivemind analytics	Tool usage stats
hivemind build "app description" [-o dir]	Autonomous app builder
hivemind upgrade [--check | -y]	Check for updates / upgrade

Run hivemind --help or hivemind <command> --help for examples and options.

---

Features

• Planner → Scheduler → Executor → Agents — DAG-based execution with configurable parallelism
• Strategy-based planning — Auto-selected strategies (research, code, data science, document, experiment) or LLM fallback
• 120+ tools — Research, coding, data science, documents, experiments, memory; smart tool selection (top-k by similarity)
• TOML config — hivemind.toml / workflow.hivemind.toml; env > project > user > defaults
• Memory & knowledge graph — Episodic, semantic, research, artifact memory; summarization, namespaces, entity/relationship search
• Map-reduce runtime — swarm.map_reduce(dataset, map_fn, reduce_fn) using the worker pool
• Workflows — Define steps in workflow.hivemind.toml; run with hivemind workflow <name>; structured output self-correction (v1.7) retries with a correction prompt when JSON parsing fails
• Critic & agent messaging (v1.7) — Optional second-pass critic scores results and requests one retry; per-run message bus lets agents share discoveries via BROADCAST:
• Speculative pre-fetching (v1.7) — Pre-warm memory and tools for successor tasks while others run; reduces standing-up time
• Plugin ecosystem — Discover tools via entry_points (hivemind.plugins)
• Provider routing — OpenAI, Anthropic, Azure, Gemini, GitHub Models (Copilot) (provider:model or model name)
• Automatic model routing — planner = "auto" and worker = "auto" for cost/latency/quality-aware selection
• EventLog, replay, telemetry — Structured events for debugging and metrics

---

Architecture

    Planner
       ↓
    Scheduler
       ↓
    Executor
       ↓
    Agents  →  Tools  →  Memory  →  Knowledge Graph

---

Configuration

Priority: env > project config > user ~/.config/hivemind/config.toml > defaults.

Locations: ./hivemind.toml, ./workflow.hivemind.toml, ~/.config/hivemind/config.toml, or legacy .hivemind/config.toml.

Keep secrets out of TOML. Use hivemind credentials or environment variables for API keys. Non-secret settings (models, workers, paths) go in TOML.

Example hivemind.toml:

[swarm]
workers = 6
adaptive_planning = true
max_iterations = 10
critic_enabled = true
critic_roles = ["research", "analysis", "code"]
message_bus_enabled = true
prefetch_enabled = true

[models]
planner = "auto"
worker = "auto"

[memory]
enabled = true
store_results = true
top_k = 5

[tools]
enabled = ["research", "coding", "documents"]
top_k = 12

[telemetry]
enabled = true
save_events = true

[providers.azure]
endpoint = ""   # or use credentials store / env
deployment = ""

Env overrides: HIVEMIND_WORKER_MODEL, HIVEMIND_PLANNER_MODEL, HIVEMIND_EVENTS_DIR, HIVEMIND_DATA_DIR, plus provider keys. Full schema: docs/configuration.md, docs/providers.md.

---

Examples

Workflow	Command
Literature review	hivemind research papers/ or uv run python examples/research/literature_review.py [dir]
Repository analysis	hivemind analyze . or uv run python examples/coding/analyze_repository.py [path]
Dataset analysis	uv run python examples/data_science/dataset_analysis.py [path-to.csv]
Document intelligence	uv run python examples/documents/analyze_documents.py [dir]
Parameter sweep	uv run python examples/experiments/parameter_sweep.py --params '{"lr":[0.01,0.1]}'

Outputs under examples/output/. Run from project root when using script paths.

---

Documentation

Full docs (with versioning and dark mode): hivemind.rithul.dev. Source lives in website/docs/ and is built with Docusaurus.

Doc	Description
Introduction	What Hivemind is, problem, core concepts
Architecture	Planner, Scheduler, Executor, Agents, Tools, Memory, strategies
Configuration	TOML schema, locations, env, credentials
Swarm runtime	Task lifecycle, flow, map-reduce
Tools	Registry, runner, smart selection, plugins
Memory	Types, store, retrieval, knowledge graph
Providers	Provider routing, Azure, GitHub Models, auto routing
CLI	All commands, credentials, completion
TUI	Layout, panels, shortcuts
Examples	Workflows and commands
Development	Structure, adding tools/plugins/workflows
Contributing	Setup, testing, PR guidelines
FAQ	Common questions

---

Contributing

Contributions welcome. See CONTRIBUTING.md.

---

License

GPL-3.0-or-later — see LICENSE.