Open-source core available nowUnlimited Skills by AI4SALE

Any agent. Any provider. One governed skill layer.

Unlimited Skills is an independent, local-first control layer for discovering, governing, routing and distributing capabilities across a mixed fleet of AI agents.

Your company may need 500 skills. Each agent needs only the right one now.

  • Local-first
  • Cross-vendor
  • Policy-ready
  • No forced migration
CodexClaude CodeOpenClawHermesCustom agents
Independent capability layer Unlimited Skills
RouteApproveAssignUpdate
01The right skillloaded only when needed
02The approved versionfrom a governed source
03The intended agentsacross teams and runtimes
184 → 1visible skill files in our context-reduction install test
90,420 → 1,268bytes of standing MCP schemas in the gateway benchmark
96.7%top-3 hit rate on the frozen 30-scenario retrieval evaluation

Reproducible project measurements, not universal performance promises.

01 / The problem

The problem begins after the first successful agent.

A useful skill is easy to install once. It becomes an operational system when the company has dozens of roles, hundreds of agents and several providers.

Discovery debt

Every team searches for the same capability again.

People hunt through repositories, compare near-duplicates and repeat installation work for every agent environment.

Security debt

Every copied skill becomes another review surface.

Unsafe instructions, prompt-injection patterns, dependencies and updates must be checked repeatedly. An approved version can quietly drift from the version agents actually run.

Context debt

More capabilities can make the agent less focused.

Loading every skill and every tool schema into standing context spends attention and tokens before the task has even started.

Control debt

Nobody can prove what reached the fleet.

Manual copies do not answer which agents received a pack, which version they use, whether policy was applied, or where an update failed.

The old workflow

Find it. Install it. Review it. Copy it. Review it again. Hope every agent has the same version.

02 / The solution

Review once. Govern centrally. Deliver everywhere.

Unlimited Skills separates the company’s capability library from every individual agent context and every individual vendor environment.

  1. 01

    Connect capability sources

    Bring together local skills, approved repositories, public collections, private packs and MCP tool definitions without moving agent workloads into another platform.

    Available now
  2. 02

    Classify, review and approve

    Keep approved, blocked, local-only and needs-review capabilities separate. Allowlist-only distribution prevents the hub from silently falling back to an unaudited catalog.

    Alpha foundation
  3. 03

    Assign by team, role and runtime

    Define which collections or private packs belong to which organisation, team, installation, agent type and release channel.

    Alpha foundation
  4. 04

    Route just in time

    The agent searches at each substantive work phase, receives at most a few candidates and loads the one capability needed now instead of carrying the whole library.

    Available now
  5. 05

    Confirm delivery and operating state

    Per-pack acknowledgements, retry state and compliance receipts will prove which version was applied to each managed agent, not merely that the installation was recently online.

    In development
03 / No vendor lock-in

Built for the fleet your business will actually have.

Sales may use one provider. Engineering another. Operations may run open-source and custom agents. Unlimited Skills is designed as a layer above those runtimes, not as another runtime you must migrate into.

Current adapters
  • Codex
  • Claude Code
  • OpenClaw
  • Hermes
Migration and extension paths
  • Vellum AI migration
  • Filesystem-based skill runtimes
  • Custom enterprise adapters

Provider coverage expands through adapters. The independent library and policy model stay the same.

04 / Edition ladder

Start free. Add control as the fleet becomes operational.

The open-source router solves capability overload today. Business and Enterprise editions turn that foundation into a governed delivery system.

Available now

Community Core

MIT / Free

For individuals and small teams that want the full local routing model without registration.

  • Local CLI and offline-first library
  • Lexical, vector and hybrid retrieval
  • One router instead of a visible wall of skills
  • Three-meta-tool MCP gateway and local savings measurement
  • Installers and native sync for supported agent runtimes
  • Local usage and feedback records with no background telemetry
Install from GitHub
Registered MVP

Team Free

Up to 10 instances

For small teams learning how governed capability sharing works before they need private distribution.

  • Create a team and connect registered installations
  • Manual master approval by default
  • Approve and revoke individual instances
  • Synchronise assigned public collections
  • Signed team-sync manifests
  • No private encrypted pack publishing
Ask about Team Free
Early access

Business Edition

Managed teams

For AI-native companies that need one operating source of skills across departments, runtimes and release cycles.

Business Edition will include

  • Larger teams and multiple Local Skill Hubs
  • Private skill packs and organisation/team assignments
  • Agent, installation and release-channel allowlists
  • Signed, versioned rollout channels with controlled rollback
  • Admin visibility, approval workflow and audit history
  • Priority compatibility support for the company’s agent stack
  • Client-side encrypted private-pack publishing in development
Design partner track

Enterprise Edition

Governed fleets

For large mixed-agent fleets where capability delivery is part of security, compliance and change management.

Enterprise Edition will include

  • Private registry with on-premises or VPC deployment options
  • Enterprise Skill Lock for approved registries, channels, signing keys and local roots
  • Centrally signed organisation policies and controlled admin override
  • Per-agent and per-pack delivery acknowledgements, retries and compliance receipts
  • Fleet dashboard for version, policy, update and failure state
  • Enterprise audit export, retention and change-control workflow
  • SSO and SCIM integration planned

Status is explicit by design: the MIT core works today; hosted collaboration, customer-facing fleet operations and some Business/Enterprise controls are alpha or in development. We do not present roadmap features as finished production software.

05 / Trust model

Stop reviewing the same skill from scratch on every agent.

The goal is a reusable approval decision: one reviewed capability, one governed version and an evidence trail showing where it is allowed to go.

Unlimited Skills does not claim that every skill is safe. It creates the controls needed to keep unreviewed, unsigned or policy-incompatible material away from managed distribution.

01

Local by default

Community search, routing and the library stay on the user’s machine. Local prompt text is not sent to a hosted service by the core.

02

Explicit review state

Approved, blocked, local-only and needs-review capabilities remain distinguishable instead of collapsing into one trusted-looking catalog.

03

Signed metadata and verified archives

Registered paths verify signed manifests, SHA256-pinned downloads and path-safe archive extraction before installation.

04

Policy-enforced sources

Enterprise Skill Lock can constrain registries, channels, signing keys, local roots, community actions and remote fallback.

06 / The difference

More than a directory. More than file sync.

A catalog helps people find skills. A control layer keeps capability choice, delivery and policy coherent after the company scales.

Typical directory or sync toolUnlimited Skills
Helps a person find a fileRoutes the right capability at the right work phase
Copies skills into one vendor environmentMaintains an independent layer across supported runtimes
Loads the whole visible catalogKeeps the library outside standing context
Treats installation as successBuilds toward versioned delivery evidence and fleet state
Security depends on each userCentralises approval, allowlists, signatures and policy
07 / Questions

What buyers usually ask first.

Does Unlimited Skills replace our AI agents?

No. It sits above supported agent runtimes as an independent capability layer. Your teams keep the providers, models and custom systems that fit each job.

Is the open-source core really free?

Yes. The local Community Core is MIT-licensed, offline-first and does not require registration for local search, routing, indexing or use.

Does the local core upload our prompts or skill bodies?

No. Local search and routing stay local. Hosted actions are explicit, registration-gated and bounded by the documented contract.

Are Business and Enterprise production-ready?

The technical foundation exists across team sync, signed manifests, private-pack clients, policy controls and governance metadata. The complete customer-facing Business and Enterprise product, including delivery receipts, encryption and the fleet dashboard, is still being productised.

Can we shape the Enterprise edition around our environment?

Yes. We are opening a design-partner track for organisations with mixed agent fleets, private skills and real governance requirements.

Talk to the product team

Bring us the fleet you no longer want to manage by hand.

Tell us where skills live, which agent runtimes use them and what your approval boundary looks like. We will map the shortest credible Business or Enterprise pilot.

Unlimited Skills inquiry

Choose an edition and tell us about your fleet.


    Protected by reCAPTCHA. The Google Privacy Policy and Terms of Service apply.