agentboards.org
Compare/Forge vs phi

Forgevsphi

Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.

Forge
Tailcall, Inc. · Terminal agent
#33OSSMCP
Panel
6.9
2 spec wins
Reliability
6.5
Usefulness
6.8
Cost
8.0
Longevity
6.2

“You summon it by typing a colon, which is the most vim thing ever to happen to a coding agent.”

phi
Pulse AI Club · Terminal agent
#28OSSMCP
Panel
6.9
2 spec wins
Reliability
7.2
Usefulness
6.5
Cost
8.0
Longevity
6.0

“Its extensions talk over a binary protocol on standard input and output, because JSON was apparently the slow part of asking a model.”

Spec by spec

SpecForgephi
Architecture
CategoryTerminal agentTerminal agent
Runslocallocal
Platformsmacos, linux, windowsmacos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientYesYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesNo
Browser controlNoNoExternal HTTP fetch is available only through an MCP server you configure.
Sandboxed executionNoNo
Multi-agent orchestrationYesYes
Headless / CI modeNoYes"phi run -p" executes one agent loop headlessly, and a headless-strict mode is one of the configurable permission modes.
Models
BackboneClaude, GPT, Gemini, Grok, DeepSeekOpenAI-compatible, Anthropic
Bring your own modelYesYes
Local modelsNoYesAny OpenAI-compatible base URL can be configured, including a locally served endpoint.
Cost
Pricing modelbyokbyok
Starts atn/a$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseApache-2.0MIT
GitHub stars7,638524

Which one would each critic pick

CriticForgephiPick
El Juez——not enough reviews
El Amigo7.07.3phi — Pick phi if you have ever had an agent quietly mangle a file; pick a more forgiving terminal agent if you would rather it guessed than stopped.
El Crítico6.86.3Forge — Setup inserts it into the interactive path of your shell, so a coding agent with command execution now sits between you and every line you type.
El Profesor7.37.5phi — Sub-agents run isolated jobs whose turns stay out of the parent's context while remaining visible in the interface, which separates what the operator sees from what the model reads.
La Inversora6.35.5Forge — Tailcall ships this open with optional Forge Services layered on, and no price attached to those services, which means the business model is still being drafted.
La Jefa6.06.3phi — Free at any headcount, and it runs one loop non-interactively with a strict headless permission mode, which makes it the rare desktop tool that can also be a pipeline step.
El Hacker8.08.8phi — MIT, any compatible base URL including one I serve myself, and tool servers listed by name only until the agent calls list, inspect and invoke to reach them on demand.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Want a third column? The compare tool handles any two agents. Three-way comparisons are on the roadmap once the spec rows are all verified.