CoreCodervsOpenABCode
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
CoreCoder
He Yufeng · Terminal agent
#215OSS
Panel
5.94 spec wins
- Reliability
- 5.5
- Usefulness
- 5.2
- Cost
- 7.8
- Longevity
- 5.0
“It ships eight essays explaining its own source code, which is eight more than most agents ship.”
OpenABCode
MatrixMap AI · Terminal agent
#176OSS
Panel
5.90 spec wins
- Reliability
- 5.8
- Usefulness
- 6.2
- Cost
- 6.7
- Longevity
- 5.0
“Its default rules send review work to one vendor and everything else to another, which is diplomacy rather than engineering.”
Spec by spec
| Spec | CoreCoder | OpenABCode |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | No | No |
| Browser control | No | No |
| Sandboxed execution | No | NoOpenABCode has no permission system of its own; the docs describe running it under a Gondolin micro-VM, plain Docker or OpenShell for isolation. |
| Multi-agent orchestration | Yes | No |
| Headless / CI mode | Yes`corecoder -p` runs a single prompt non-interactively, but the tool guard is a regex blacklist, not a security sandbox. | No |
| Models | ||
| Backbone | any OpenAI-compatible endpoint, Ollama, LiteLLM | Anthropic Claude, OpenAI, Google Gemini |
| Bring your own model | Yes | Yes |
| Local models | YesDocumented with a local Ollama endpoint via OPENAI_BASE_URL, and an optional LiteLLM backend for other providers. | No |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | AGPL-3.0 |
| GitHub stars | 1,788 | 427 |
Which one would each critic pick
| Critic | CoreCoder | OpenABCode | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.0 | 6.3 | OpenABCode — Pick it if you already pay three providers and want the choice made for you; pick a single-model agent if you only have one bill. |
| El Crítico | 5.5 | 5.8 | OpenABCode — It ships no permission system of its own, and the documentation answers that by describing micro-VM, Docker and policy-sandbox patterns you set up yourself. |
| El Profesor | 7.0 | 6.3 | CoreCoder — 1,217 lines cover the loop, model interface, context, tools and sessions, with three-tier compaction and a per-run token and cost report; the protocol layer is deliberately absent. |
| La Inversora | 4.3 | 5.5 | OpenABCode — 358 stars and a product whose function is arbitrage between three model vendors, any one of which can price the arbitrage away. |
| La Jefa | 4.3 | 4.8 | OpenABCode — Routing across three vendors means three contracts, three data paths and three invoices for sixty engineers, and no SSO or audit log over any of them. |
| El Hacker | 8.3 | 7.0 | CoreCoder — MIT, one pip command, and a base URL environment variable pointed at my own server, with an optional router underneath for everything else. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.