Agentic Index
Refact.ai vs Tabby (2026)
Both are open source and self hosted; the split is agent against assistant. Refact is an autonomous agent, ranked first among open source agents on SWE-bench Verified, that plans, edits, runs tests, and iterates, with zero telemetry self hosting. Tabby is a fast completion and codebase answer server, lighter to run, and entirely free with no paid tiers.
| At a glance | Refact.ai | Tabby |
|---|---|---|
| Category | Coding agent | Coding agent |
| Entry price | Free tier includes unlimited code completions, core agent access, and BYOK. Paid plans start around ten dollars a month. Extra coins cost one dollar per thousand with a five dollar minimum and never expire. Self hosting the open source edition is free. | Free and open source. No seats, subscriptions, or usage limits. The only cost is the hardware or cloud graphics compute that runs the self hosted server. |
| Free / trial | A genuinely free tier includes unlimited code completions, core AI agent access, a monthly allowance of five thousand coins, and bring your own key support. The open source edition is also free to self host. | Tabby is entirely free and open source with no paid tier required. It is not a trial; the full product runs at no license cost on the team's own infrastructure. |
| Pricing confidence | public exact | public exact |
| Feature |
T
Tabby
|
|
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
Full / Explicit | Partial |
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
Full / Explicit | Partial |
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
Partial | Partial |
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
Full / Explicit | Partial |
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
No / Not documented | No / Not documented |
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
Partial | Partial |
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
Partial | Partial |
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
Partial | Partial |
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
Full / Explicit | Full / Explicit |
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
No / Not documented | No / Not documented |
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
Full / Explicit | Partial |
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
Partial | Partial |
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
Partial | No / Not documented |
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
Partial | No / Not documented |
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing |
T
Tabby
|
|
|---|---|---|
|
Entry price Lowest public entry point |
Free tier includes unlimited code completions, core agent access, and BYOK. Paid plans start around ten dollars a month. Extra coins cost one dollar per thousand with a five dollar minimum and never expire. Self hosting the open source edition is free. | Free and open source. No seats, subscriptions, or usage limits. The only cost is the hardware or cloud graphics compute that runs the self hosted server. |
|
Pricing confidence How public the numbers are |
Public — exact | Public — exact |
|
Billing Primary billing axis |
Coin based usage plus a paid subscription. A free monthly coin allowance and unlimited completions come at no cost. Paid plans lift limits from around ten dollars a month, and extra coins cost one dollar per thousand with a five dollar minimum. Bringing your own model key runs the agent at no coin cost, so you pay only your provider. | There is no product billing. Tabby is free and open source, so the only cost is the infrastructure that runs the self hosted server, whether a workstation, a dedicated server, or cloud graphics compute. |
|
Variable cost Workload / overage exposure |
High variable cost | Low variable cost |
|
Free tier / trial Try before you buy |
Free tier
|
Free tier
|
|
Buying motion Self-serve vs sales call |
Self-serve | Self-serve |
Choose Refact.ai if
- You want end to end task completion on your own servers, not just suggestions.
- The SWE-bench Verified record, 352 of 500 issues, is reproducible and open.
- BYOK flexibility across providers or local models runs the agent at raw cost.
Choose Tabby if
- Fast completion and codebase answers cover your actual need; agents are premature.
- Simplest possible self hosting: one binary or container on consumer GPUs.
- Truly free at any team size, with cost limited to hardware.