Claude Code Agents, Compared
Compatibility here means full support, read from each agent's own AGENTS.md and documentation rather than inferred from the fact that it is an agent. Agents that only partly work under Claude Code are left out on purpose — a partial listing is the kind that costs you an afternoon.
| # | Agent | FARS | Trust | Stars | License | Language | Last commit |
|---|---|---|---|---|---|---|---|
| 1 | AGF Local Coding Session Finder | 96 | 27/25 | 158 | MIT | Rust | 2026-10-01 |
| 2 | Argot Repository Style Analyzer | 93 | 28/25 | 51 | MIT | Rust | 2026-09-02 |
| 3 | Material Learning Studio | 92 | 25/25 | 1.1k | MIT | Python | 2026-10-07 |
| 4 | jev-axi Judgment CLI | 90 | 23/25 | 43 | MIT | TypeScript | 2026-09-24 |
| 5 | QuantDinger AI Trading OS | 89 | 25/25 | 12.9k | Apache-2.0 | Python | 2026-10-19 |
| 6 | Zoetrope | 89 | 23/25 | 1.1k | MIT | Rust | 2026-09-11 |
| 7 | agnix Config Linter | 89 | 27/25 | 455 | Apache-2.0 | Rust | 2026-10-18 |
| 8 | Mirafold | 89 | 25/25 | 18 | MIT | TypeScript | 2026-09-16 |
| 9 | Piia Engram | 88 | 27/25 | 162 | AGPL-3.0 | Python | 2026-10-10 |
| 10 | YYLO CLI | 88 | 25/25 | 65 | MIT | Python | 2026-10-15 |
| 11 | Blave Agent | 87 | 25/25 | 113 | Apache-2.0 | Python | 2026-10-19 |
| 12 | myc Local Agent Memory | 87 | 24/25 | 14 | MIT | TypeScript | 2026-10-18 |
The order is the FARS total; stars only break ties, because popularity measures attention rather than whether something holds up. Two limits are worth knowing before you read the order. These are static reviews — source, documentation and repository metadata, with no runtime reproduction — which caps reliability, effectiveness and verifiability and puts the achievable maximum at 77 rather than 100. And a gap of a few points sits inside the noise of that method. Read the table as a shortlist worth investigating, not as a verdict; every score links to its full dimension breakdown and the evidence behind it. Review method →
1. AGF Local Coding Session Finder
Search and resume locally stored AI coding sessions from one terminal interface.
Where it differs
Compared with opening each agent's native session picker or manually searching history files, AGF provides one searchable view across 16 tools plus common JSON and MCP query interfaces. It does not replace those agents, however: each native CLI still performs the resume, and some providers' sessions must be deleted through their own picker to preserve upstream state.
2. Argot Repository Style Analyzer
Learn unwritten conventions from Git history and flag changes that diverge from the repository.
Where it differs
A type checker asks whether code satisfies its type constraints; Argot asks whether a change resembles the code, layout, and dependency direction established by that repository. Unlike sending the code to a second LLM for an opinion, Argot derives findings from local statistical, graph, scripted, and embedding evidence, with no generative or opinion-forming model deciding the result. The tradeoff is that it remains a repository-specific review guardrail, not a general correctness oracle.
3. Material Learning Studio
Turn books, papers, and office documents into traceable, testable, offline learning pages.
Where it differs
The repository explicitly derives from two MIT-licensed projects: virgiliojr94/book-to-skill supplies material extraction, knowledge decomposition, and the base knowledge-base structure, while crayon-ai/book-to-webpage supplies the interactive page, themes, source display, and follow-up interaction design. learn-from-materials extends that foundation with a cross-agent Agent Skills workflow, two study depths, a versioned method library, an integrated whole-material methodology, coverage and content-review records, and an offline delivery pipeline. The upstream projects may be a narrower fit when only their foundational extraction or webpage conversion scope is needed; this repository is the broader option when one workflow must produce source-audited learning artifacts and reusable method records.
4. jev-axi Judgment CLI
Fast probabilistic safety and workflow judgments for coding agents, shell commands, diffs, logs, and untrusted text.
Where it differs
Unlike foreman, which runs Jev as a supervisor above a coding agent, jev-axi does not launch the agent; it connects similar completion and progress judgments to the agent's existing hooks. It also differs from generative coding models: Jev returns typed probabilistic judgments and never writes prose, so jev-axi complements rather than replaces code generation and code comprehension.
5. QuantDinger AI Trading OS
Turn AI-assisted market research into Python strategies, backtests, paper trading, live execution, and monitoring.
Where it differs
Unlike a black-box signal service, QuantDinger keeps strategy code, risk settings, credentials, and deployment under the operator's control. Unlike a design tied to one model vendor, it documents OpenRouter, OpenAI-compatible APIs, Google, DeepSeek, Grok, MiniMax, and custom endpoints, although each still requires its own configuration and service access. The base Compose stack also differs from an always-on monitoring bundle: Prometheus, Grafana, and Alertmanager are optional through the observability overlay.
6. Zoetrope
Watch a Claude Code session as a live flow graph — main agent, subagents and tool calls — in your terminal or browser.
7. agnix Config Linter
Find and fix broken AI coding-assistant configurations before they disrupt development workflows.
8. Mirafold
Run and supervise your local coding agents from a browser.
Where it differs
Compared with using Claude Agent, Codex, OpenCode, or Gemini CLI directly in a terminal, Mirafold keeps the native agent and its local permission model while adding a browser UI, structured generative components, multi-session supervision, and adjacent file and Git views. It is not a unified proxy agent and does not replace those CLIs with its own generic implementation. Each supported agent has a separate adapter, so live availability still depends on that backend and its authentication.
9. Piia Engram
A user-owned local identity and long-term knowledge layer shared across AI coding tools.
Where it differs
Compared with Claude Memory, Piia Engram keeps its records in user-controlled local files and targets multiple MCP tools instead of the Claude ecosystem alone. Compared with CLAUDE.md or .cursorrules, it preserves personal preferences, lessons, and decisions across repositories; repository rule files remain the better place for project-specific build steps and conventions. Mem0, Zep, and Letta focus on task or session memory for agents, whereas Piia Engram focuses on the person behind those tasks and their enduring work standards. The official @modelcontextprotocol/server-memory provides a generic entity-relation knowledge graph, while Piia Engram adds structures specifically for developer identity, quality standards, lessons, decisions, and governed review.
10. YYLO CLI
Orchestrate coding agents, repository tasks, validation, and protected merges with durable receipts.
11. Blave Agent
Turn trading ideas into tested strategies and live deterministic execution with Claude Code or Codex.
Where it differs
With a user's own Claude Code or Codex, the desktop app only launches the CLI, requires no Blave account, and adds no Blave AI charge; the user remains responsible for their existing AI subscription or service costs. Blave AI is the built-in alternative and requires a Blave account with usage-based billing. Local desktop operation is free and keeps workspace credentials on the user's machine, but orders run only while the app is open. The paid cloud-machine option runs continuously and can be reached through the web workspace, Telegram, or SSH.
12. myc Local Agent Memory
A local task, durable-memory, and code-intelligence layer for coding agents.
Where it differs
Compared with beads, myc is more than an importer: it supplies its own task graph, memory, retrieval, and agent-integration layer. myc import-beads --dry-run previews a migration, while the full importer can carry tasks, dependencies, comments, memories, and supported metadata and later operate as a sync. It reports one-sided edits and two-sided conflicts instead of silently overwriting local changes. Its ready queue also models blockers inherited through parent tasks, correcting an earlier mismatch with beads. Adoption from beads still depends on a usable bd export --include-memories snapshot, and conflicting edits can require manual resolution.