Architect is planning your project...
WHY ARCHITECT

The problem.

Every agent framework runs tasks sequentially. Give an agent "build me a landing page with auth and monitoring" and it runs one step at a time. But most complex tasks have independent subtasks that could run in parallel.

Worse: when two agents on the network both need to "deploy a React app to Kubernetes," each one spends 3-8 seconds asking an LLM to decompose the task from scratch. The second agent learns nothing from the first.

Architect finds the parallelism, and the network remembers the plan so nobody solves it twice.

CACHE RESOLUTION

Five steps. Skip inference.

Architect tries to skip LLM inference entirely. Only generates a new plan when no cached version exists anywhere on the network.

NORMALIZE
Strip, sort, hash
LOCAL
SHA-256 ~2ms
SIMILAR
MinHash ~15ms
PEERS
DHT ~200ms
INFER
LLM ~3-8s

Each resolution caches the result — future lookups are faster for everyone

NETWORK EFFECT

Why P2P gossip changes everything.

On a centralized platform, cached plans live on one server. On Hyperspace, every node contributes to and benefits from a shared plan cache. This creates a compounding network effect.

ChannelTopicEffect
Announcementshyperspace/dag-cache/announcementsNew DAG cached → broadcast to all peers
DHT Providers/dag-plans/<hash>Register as provider → peers fetch on demand
Quality feedbackhyperspace/dag-cache/outcomesBad plans auto-evict (<60% success rate)

The network is a self-curating library of task decomposition strategies. Good plans rise. Bad plans die.

ARCHITECTURE

Four layers. One cache.

Similarity Index
MinHash (128 hash functions) + cosine verification. "Build React page" matches "Create React page" at 0.82 similarity.
DHT Resolver
Provider records at /dag-plans/<hash>. GossipSub announcements. Fetch plans from any peer via protocol stream.
Content Store
SHA-256 content addressing. LRU (10K entries, 7-day TTL). Plans with <60% success rate auto-evict after 5 samples.
Normalization
Lowercase, strip stop words, sort keywords. "Build a React landing page" and "build landing page React" hash identically.
PERFORMANCE

What you save.

ResolutionLatencyTokensWhen
Local cache hit~2ms0Same task, same node
Similarity match~15ms0Similar task, same node
DHT peer hit~200ms0Any task, any node
Architect inference~3-8s500-2KNovel task, no cache

As the network grows, the ratio of cache hits to inference approaches 1.0. The marginal cost of task decomposition trends toward zero.

INSTALL

Start contributing DAGs.

CLI
# Install the Hyperspace CLI
curl -fsSL https://agents.hyper.space/api/install | bash

# Start your node
hyperspace start

# Decompose a task
hyperspace architect "deploy my app to kubernetes with monitoring"