Framework
19 records filed under this subject, newest first, each with what it is, what it cost and where the builder got stuck.
Records
19
131AntOmniEvoA Python framework that runs an evolution loop over a directory of your files: a coding agent rewrites them from the failure trajectories of the previous candidate, parent and child are scored on the same training batch, and only an improvement that clears a threshold is re-scored on the validation set and kept.ClaudeClaude Code
129Agents UniverseAn open-source agent platform that keeps one project context shared by everyone working in it. Agents read the whole knowledge base when a project is opened and write what they learn back into the same files while they work; knowledge is Markdown on disk with a database index behind it, and there is no embedding model or vector search.ClaudeClaude CodeGemini+1
119headcountAn agent organization shaped like a company — a chief executive over sixteen independently installable departments and 172 skills, where a skill is a folder of Markdown that loads itself when a request matches its description, one tree installs in both Claude Code and ChatGPT because only the manifests differ, and the 184 outside authorities that settle a question rather than decorate an answer — a regulator, a standards body, primary law — sit in a catalog beside the skills they answer for, each labeled with what an agent may do with it.ClaudeClaude CodeCodex+2
102DeepSeek HarnessDeepSeek’s agent harness, built so that the model adapter, the tool registry, the session log and the agent loop itself are plugins — swapped from a configuration file rather than a fork.DeepSeekClaude CodeCodex
100VibeGameDescribe a game in one sentence and a team of agents divides the work — an architect plans it, a programmer builds it, an auditor checks the code against the plan, and a player has to actually play it before the task is accepted.Claude CodeCodex
090CambiumA governance standard for the knowledge corpora that LLM agents maintain, shipped together with the reference toolset that executes it: a normative kernel of numbered domains that a per-repository profile may tighten but never switch off, three ledgers that have to agree, deterministic tools that check, write and compile, and append-only receipts that decide which evidence must exist before work is allowed to close.ClaudeClaude CodeCodex+1
085TrueForgeA self-hosted runtime that takes over the agent loop — model calls, MCP tool servers, git-backed skills, an optional sandbox, human approvals, context compaction and session state — and hands it back three ways: a chat UI, an HTTP API with a TypeScript SDK, and an embeddable UI SDK, on SQLite in a single process or on Postgres and Redis when it is hosted.Claude CodeCursorRailway+1
071Open Mercato SkillsA pack of forty-one agent skills that installs into any repository and runs the whole pull-request pipeline — plan, implement in an isolated worktree, self-review, browser-checked QA, merge — with three entry paths (a task brief, a specification, or a tracker issue) converging on one review loop, every project-specific value read from a single committed configuration file, tracker commands confined to committed descriptor documents shipped for GitHub, GitLab, Linear and Jira, and each skill handing the next one a machine-parsed PR reference line.ClaudeClaude CodeCodex+1
065GSD CoreGit. Ship. Done. — a meta-prompting, context-engineering and spec-driven development framework that runs the same five-step loop on every milestone: discuss, plan, execute, verify and ship. The heavy work is pushed into fresh-context subagents so the main session stays lean, and every decision is written into Markdown and JSON under a planning directory instead of living in the conversation.Claude CodeClaudeCodex+7
059gate4agentA Rust workbench for running, watching and orchestrating CLI coding agents across machines — wrapping Claude Code, Codex, Kimi and Grok behind one transport, one relay and one operator protocol.ClaudeClaude Code
060Nuwa SkillA skill that distils a person’s thinking — mental models, decision heuristics, the way they talk — into a reusable agent persona, and scores the result against a fidelity rubric before anyone else is allowed to use it.ClaudeClaude Code
056DistillyA skill that turns a person’s messages, documents and interviews into a reusable profile — their experience, judgement and way of working — and states plainly that a profile is not a clone of the person.ClaudeClaude Code
054AI Job SearchA job-application framework that runs on your own machine: it scores postings against a profile you fill in, drafts a tailored CV and cover letter in LaTeX, compiles them, reads the rendered PDF back — and stops one step short of sending anything.ClaudeClaude Code
050gstackTwenty-three specialist roles and eight power tools for Claude Code, all written as Markdown slash commands, plus the evaluation harness their author uses to decide whether any of it is working.ClaudeClaude CodeCursor+1
046Claude Code Game StudiosA Claude Code configuration that behaves like a game studio: forty-nine agent definitions arranged as a studio hierarchy, seventy-odd skills, hooks that gate commits and pushes, and a set of documents a change has to pass through.ClaudeClaude Code
035Nexus AgentsA control plane that sits above coding agents rather than being one: it admits work through a single entry point, puts every real fork to a multi-agent vote, records every action in a hash-chained audit log, and requires the repository owner to ratify any change to the rules that govern it.ClaudeClaude CodeCodex+1
031Agency AgentsOne markdown file per AI specialist persona, organised into divisions like engineering, marketing and healthcare, and installed by script or by a desktop app into a dozen different coding tools.ClaudeClaude Code
012CrewAIAgents get a role, a goal and a backstory; a crew runs several of them on one task.GPTClaude
006DifyA visual workspace for building agentic workflows and RAG pipelines, run from Docker or from the vendor’s cloud.GPTClaudeDeepSeek