agentjido/jido_ai
71.6
Strong · 15 November 2026
44.2k
lines of production code
Elixir
primary language
5
measurements over time
What this system is
Features
Initial release of Jido.AI agent framework and project scaffolding
This change introduces the Jido.AI package, an Elixir runtime for building tool-using AI agents with explicit reasoning strategies (ReAct, Chain-of-Thought, Tree-of-Thoughts, etc.) and production-ready request orchestration. It establishes the core architecture including \Jido.AI.Agent\, \Jido.AI.Actions\, and plugin-based strategy execution, replacing the previous v1.x Instructor-based implementation. The release also adds comprehensive project scaffolding, including an Igniter installer for automated setup, environment variable examples for local development, and detailed documentation (AGENTS.md, README, usage rules) to guide developers in defining tools, configuring model aliases, and running synchronous or asynchronous agent requests.
(repo-wide) · high confidence
New CLI tasks for Jido AI installation, execution, skills, and quality checks
This release introduces four new Mix tasks in the \lib/mix/tasks\ directory to streamline Jido AI usage. \mix jido\_ai.install\ automates project setup using Igniter, configuring default model aliases and prompting for API keys. \mix jido\_ai\ provides a unified command-line interface for running AI agents in one-shot or batch (stdin) modes, supporting various reasoning types (e.g., ReAct, Chain-of-Thought) and output formats. \mix jido\_ai.skill\ allows users to list, inspect, and validate AI skill definitions from directories or specific files. Finally, \mix jido\_ai.quality\ offers a maintainer-focused checkpoint that runs fast and full test gates and verifies traceability closure against a story matrix.
lib/mix · high confidence
New Jido.AI skill actions for LLM, planning, and quota management
The \lib/jido\_ai\ library introduces a new set of Jido.Action modules that expose AI capabilities as reusable skills. This includes LLM actions for chat (\llm\_chat\), text completion (\llm\_complete\), embedding (\llm\_embed\), and structured object generation (\llm\_generate\_object\), all of which support model aliases, context-based defaults, and telemetry. Planning skills allow for goal decomposition (\planning\_decompose\), structured plan generation (\planning\_plan\), and task prioritization (\planning\_prioritize\). Additionally, quota management actions (\quota\_get\_status\, \quota\_reset\) are provided to track and reset usage limits. These actions share a common helper module (\Jido.AI.Actions.Helpers\) for input validation, model resolution, and telemetry metadata.
_lib/jido\ai · high confidence
New example agents and tools for API testing, web browsing, and GitHub triage
The examples directory now includes several new demonstration agents: an API smoke test agent for iterative HTTP debugging, a browser agent for reading and summarizing web pages, an issue triage agent for GitHub repositories, a task list agent for planning and executing multi-step goals, and a calculator agent using skills. These examples also introduce new tools for browser interaction (reading pages, searching the web, snapshotting URLs) and compatibility fallbacks for legacy weather tools, alongside a new README with instructions for running the demos.
examples · high confidence
Behavioural changes
New configuration structure for logging, git hooks, and versioning
The application now uses a new configuration structure (config/config.exs, dev.exs, test.exs) that standardizes logger metadata to include Jido.AI context and error details. In development, git hooks are configured to enforce commit message formatting via git\_ops and check code formatting on push, while test environments suppress most logs and disable auto-installed hooks.
config · high confidence
Renamed JidoAi to Jido.AI and introduced model alias resolution
The core library module has been renamed from JidoAi to Jido.AI, bringing with it a comprehensive set of new capabilities for managing AI interactions. Users can now configure and resolve semantic model aliases (such as :fast or :capable) instead of hardcoding provider strings, and set role-based LLM defaults for text, object, and streaming generation. The module also exposes runtime tool management APIs to register, unregister, and list tools dynamically for running agents. As part of this restructuring, the example Politician action has been removed from the library.
lib · high confidence
Test coverage
Added comprehensive test coverage for Jido.AI core components; Added comprehensive test coverage for the ReAct reasoning runtime; Added concurrency and migration tests for AI quota and retrieval stores; Added integration tests for plugin lifecycle, schemas, and signal routing; Added live integration tests for request streaming and stream timeout handling; Added test coverage for CLI reasoning agent adapters and mix task contract; Added test coverage for the Jido.AI.Skill system; Added test coverage for the TRM reasoning engine components; Added test support utilities for CLI, directives, and LLM mocking; Added tests for AI signal helper functions; Added tests for Chain of Thought reasoning plugin; Added tests for Graph-of-Thoughts machine logic and structure enforcement; Added tests for ReAct action helpers and runtime actions; Added tests for Tree-of-Thoughts reasoning machine and structure enforcement; Added tests for directive deadlock prevention and error handling; Added tests for error model normalization and message sanitization; Added tests for example agents and weather tools; Added tests for reasoning strategy entrypoints, helper observability, and request lifecycle; Added tests for reasoning strategy plugins; Added tests for skill loading and resource access actions; Added tests for the Chat plugin specification and configuration; Added tests for the Planning plugin's specification, initialization, and action routing; Added tests for the Reasoning plugin and its security validations; Added unit and integration tests for AI reasoning strategies; Added unit tests for Planning skill actions; Added unit tests for Planning skill actions; Added unit tests for reasoning skill actions and strategy execution; Added unit tests for tool-calling actions; Expanded integration test coverage for Jido.AI v2 migration and strategy behaviors; Expanded test coverage for Jido.AI module and test infrastructure updates.
Dependencies
Jido AI v2.3.0 release with ecosystem dependency upgrades
This release updates the project to version 2.3.0 and aligns the Elixir requirement to version 1.18. It upgrades core Jido ecosystem dependencies, including jido to \~\> 2.3, jido\_action to \~\> 2.3, and req\_llm to \~\> 1.14. Several runtime and development dependencies are also updated, such as mimic to \~\> 2.0, ex\_doc to \~\> 0.31, and credo to \~\> 1.7, while adding new dependencies like fsmx, splode, and yaml\_elixir to support the expanded feature set.
(dependencies) · high confidence
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
How this codebase got here
Score
- CAI 74 → 72 (-1.9)
- Rubric changed (rubric-2026.11.1 → rubric-2026.11.4) — scores are not directly comparable.
Lenses
- Code Health 93 → 89 (-3.9)
- Architecture 89 → 99 (+10.7)
- Maturity 68 → 68 (-0.0)
- Readiness 74 → 74 (-0.1)
- Security 78 → 68 (-10.5)
Resolved (7)
- Duplicated block (4–6 lines × 3) (lib/jido_ai/actions/tool_calling/call_with_tools.ex)
- Medium CVE: EEF-[CVE redacted] (mix.lock)
- Members sharing a duplicated core (6 members, 50+ identical tokens) (lib/jido_ai/reasoning/algorithm_of_thoughts/strategy.ex)
- Off-boarding risk: anonymized user #1
- Outdated: mimic
- Projects may be oversized for their cohesion
- Repeated repair: lib/jido_ai/output.ex (lib/jido_ai/output.ex)
New (94)
- Change coupling: agent.ex ↔ state.ex (lib/jido_ai/agent.ex)
- Edited copies of one member (3 members, 10+ corresponding lines) (examples/lib/tools/unit_converter.ex)
- Edited copies of one member (3 members, 16+ corresponding lines) (lib/jido_ai/reasoning/chain_of_thought/machine.ex)
- Edited copies of one member (3 members, 19+ corresponding lines) (lib/jido_ai/reasoning/graph_of_thoughts/strategy.ex)
- Edited copies of one member (3 members, 22+ corresponding lines) (lib/jido_ai/reasoning/graph_of_thoughts/strategy.ex)
- Edited copies of one member (3 members, 23+ corresponding lines) (lib/jido_ai/turn.ex)
- Edited copies of one member (3 members, 25+ corresponding lines) (examples/lib/tools/task_list.ex)
- Edited copies of one member (3 members, 27+ corresponding lines) (lib/jido_ai/actions/llm/chat.ex)
- Edited copies of one member (3 members, 3+ corresponding lines) (lib/jido_ai/reasoning/graph_of_thoughts/strategy.ex)
- Edited copies of one member (3 members, 4+ corresponding lines) (lib/jido_ai/directive/llm_generate.ex)
- Edited copies of one member (3 members, 4+ corresponding lines) (lib/jido_ai/reasoning/algorithm_of_thoughts/machine.ex)
- Edited copies of one member (3 members, 7+ corresponding lines) (lib/jido_ai.ex)
- Edited copies of one member (3 members, 8+ corresponding lines) (lib/jido_ai/output.ex)
- Edited copies of one member (4 members, 26+ corresponding lines) (examples/lib/compat/weather_tools_fallback.ex)
- Edited copies of one member (4 members, 3+ corresponding lines) (lib/jido_ai/reasoning/algorithm_of_thoughts/strategy.ex)
- Edited copies of one member (4 members, 33+ corresponding lines) (lib/jido_ai/actions/llm/chat.ex)
- Edited copies of one member (4 members, 4+ corresponding lines) (lib/jido_ai/actions/skill/load_skill.ex)
- Edited copies of one member (5 members, 19+ corresponding lines) (lib/jido_ai/reasoning/adaptive/cli_adapter.ex)
- Edited copies of one member (5 members, 4+ corresponding lines) (lib/jido_ai/reasoning/algorithm_of_thoughts/machine.ex)
- Edited copies of one member (6 members, 7+ corresponding lines) (lib/jido_ai/actions/planning/decompose.ex)
- …and 74 more
Changes since last survey
- 6 commits — 2 feature/other, 4 fixes
By area
- (root) — 3 commits
- lib/jido_ai — 2 commits
- guides/user — 1 commit
Notable commits
- fix: fix(context): preserve participant names (#392)
- fix: fix(deps): update jsv to patched release (#391)
- fix: fix(react): handle mixed final tool calls (#393)
- fix: fix: expose native tool invocation IDs in action context (#389)
- change: deps(deps-dev): bump mimic from 2.4.2 to 2.5.0 (#394)
- change: docs: note V3 consolidation (#395)
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
Survey your own repository
agentjido/jido_ai was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.
About this page
- The score is its most recent published measurement, taken on 15 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
- Measured at commit 3dfae153cf873de7319dff2a866f2f75a9bdf287 — the exact code this score is about.
- Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
- Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.73+preprod-52de90b74216.