mdcontext 0.0.1 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.changeset/README.md +28 -0
- package/.changeset/config.json +11 -0
- package/.claude/settings.local.json +25 -0
- package/.github/workflows/ci.yml +83 -0
- package/.github/workflows/claude-code-review.yml +44 -0
- package/.github/workflows/claude.yml +85 -0
- package/.github/workflows/release.yml +113 -0
- package/.tldrignore +112 -0
- package/BACKLOG.md +338 -0
- package/CONTRIBUTING.md +186 -0
- package/NOTES/NOTES +44 -0
- package/README.md +434 -11
- package/biome.json +36 -0
- package/cspell.config.yaml +14 -0
- package/dist/chunk-23UPXDNL.js +3044 -0
- package/dist/chunk-2W7MO2DL.js +1366 -0
- package/dist/chunk-3NUAZGMA.js +1689 -0
- package/dist/chunk-7TOWB2XB.js +366 -0
- package/dist/chunk-7XOTOADQ.js +3065 -0
- package/dist/chunk-AH2PDM2K.js +3042 -0
- package/dist/chunk-BNXWSZ63.js +3742 -0
- package/dist/chunk-BTL5DJVU.js +3222 -0
- package/dist/chunk-HDHYG7E4.js +104 -0
- package/dist/chunk-HLR4KZBP.js +3234 -0
- package/dist/chunk-IP3FRFEB.js +1045 -0
- package/dist/chunk-KHU56VDO.js +3042 -0
- package/dist/chunk-KRYIFLQR.js +88 -0
- package/dist/chunk-LBSDNLEM.js +287 -0
- package/dist/chunk-MNTQ7HCP.js +2643 -0
- package/dist/chunk-MUJELQQ6.js +1387 -0
- package/dist/chunk-MXJGMSLV.js +2199 -0
- package/dist/chunk-N6QJGC3Z.js +2636 -0
- package/dist/chunk-OBELGBPM.js +1713 -0
- package/dist/chunk-OT7R5XTA.js +3192 -0
- package/dist/chunk-P7X4RA2T.js +106 -0
- package/dist/chunk-PIDUQNC2.js +3185 -0
- package/dist/chunk-POGCDIH4.js +3187 -0
- package/dist/chunk-PSIEOQGZ.js +3043 -0
- package/dist/chunk-PVRT3IHA.js +3238 -0
- package/dist/chunk-QNN4TT23.js +1430 -0
- package/dist/chunk-RE3R45RJ.js +3042 -0
- package/dist/chunk-S7E6TFX6.js +803 -0
- package/dist/chunk-SG6GLU4U.js +1378 -0
- package/dist/chunk-SJCDV2ST.js +274 -0
- package/dist/chunk-SYE5XLF3.js +104 -0
- package/dist/chunk-T5VLYBZD.js +103 -0
- package/dist/chunk-TOQB7VWU.js +3238 -0
- package/dist/chunk-VFNMZ4ZQ.js +3228 -0
- package/dist/chunk-VVTGZNBT.js +1629 -0
- package/dist/chunk-W7Q4RFEV.js +104 -0
- package/dist/chunk-XTYYVRLO.js +3190 -0
- package/dist/chunk-Y6MDYVJD.js +3063 -0
- package/dist/cli/main.d.ts +1 -0
- package/dist/cli/main.js +5458 -0
- package/dist/index.d.ts +653 -0
- package/dist/index.js +79 -0
- package/dist/mcp/server.d.ts +1 -0
- package/dist/mcp/server.js +472 -0
- package/dist/schema-BAWSG7KY.js +22 -0
- package/dist/schema-E3QUPL26.js +20 -0
- package/dist/schema-EHL7WUT6.js +20 -0
- package/docs/019-USAGE.md +625 -0
- package/docs/020-current-implementation.md +364 -0
- package/docs/021-DOGFOODING-FINDINGS.md +175 -0
- package/docs/BACKLOG.md +80 -0
- package/docs/CONFIG.md +1123 -0
- package/docs/DESIGN.md +439 -0
- package/docs/ERRORS.md +383 -0
- package/docs/PROJECT.md +88 -0
- package/docs/ROADMAP.md +407 -0
- package/docs/summarization.md +320 -0
- package/docs/test-links.md +9 -0
- package/justfile +40 -0
- package/package.json +74 -9
- package/pnpm-workspace.yaml +5 -0
- package/research/INDEX.md +315 -0
- package/research/code-review/README.md +90 -0
- package/research/code-review/cli-error-handling-review.md +979 -0
- package/research/code-review/code-review-validation-report.md +464 -0
- package/research/code-review/main-ts-review.md +1128 -0
- package/research/config-analysis/01-current-implementation.md +470 -0
- package/research/config-analysis/02-strategy-recommendation.md +428 -0
- package/research/config-analysis/03-task-candidates.md +715 -0
- package/research/config-analysis/033-research-configuration-management.md +828 -0
- package/research/config-analysis/034-research-effect-cli-config.md +1504 -0
- package/research/config-analysis/04-consolidated-task-candidates.md +277 -0
- package/research/config-docs/SUMMARY.md +357 -0
- package/research/config-docs/TEST-RESULTS.md +776 -0
- package/research/config-docs/TODO.md +542 -0
- package/research/config-docs/analysis.md +744 -0
- package/research/config-docs/fix-validation.md +502 -0
- package/research/config-docs/help-audit.md +264 -0
- package/research/config-docs/help-system-analysis.md +890 -0
- package/research/dogfood/consolidated-tool-evaluation.md +373 -0
- package/research/dogfood/strategy-a/a-synthesis.md +184 -0
- package/research/dogfood/strategy-a/a1-docs.md +226 -0
- package/research/dogfood/strategy-a/a2-amorphic.md +156 -0
- package/research/dogfood/strategy-a/a3-llm.md +164 -0
- package/research/dogfood/strategy-b/b-synthesis.md +228 -0
- package/research/dogfood/strategy-b/b1-architecture.md +207 -0
- package/research/dogfood/strategy-b/b2-gaps.md +258 -0
- package/research/dogfood/strategy-b/b3-workflows.md +250 -0
- package/research/dogfood/strategy-c/c-synthesis.md +451 -0
- package/research/dogfood/strategy-c/c1-explorer.md +192 -0
- package/research/dogfood/strategy-c/c2-diver-memory.md +145 -0
- package/research/dogfood/strategy-c/c3-diver-control.md +148 -0
- package/research/dogfood/strategy-c/c4-diver-failure.md +151 -0
- package/research/dogfood/strategy-c/c5-diver-execution.md +221 -0
- package/research/dogfood/strategy-c/c6-diver-org.md +221 -0
- package/research/effect-cli-error-handling.md +845 -0
- package/research/effect-errors-as-values.md +943 -0
- package/research/errors-task-analysis/00-consolidated-tasks.md +207 -0
- package/research/errors-task-analysis/cli-commands-analysis.md +909 -0
- package/research/errors-task-analysis/embeddings-analysis.md +709 -0
- package/research/errors-task-analysis/index-search-analysis.md +812 -0
- package/research/frontmatter/COMMENTS-ARE-SKIPPED.md +149 -0
- package/research/frontmatter/LLM-CODE-NAVIGATION.md +276 -0
- package/research/issue-review.md +603 -0
- package/research/llm-summarization/agent-cli-tools-2026.md +1082 -0
- package/research/llm-summarization/alternative-providers-2026.md +1428 -0
- package/research/llm-summarization/anthropic-2026.md +367 -0
- package/research/llm-summarization/claude-cli-integration.md +1706 -0
- package/research/llm-summarization/cli-integration-patterns.md +3155 -0
- package/research/llm-summarization/openai-2026.md +473 -0
- package/research/llm-summarization/openai-compatible-providers-2026.md +1022 -0
- package/research/llm-summarization/opencode-cli-integration.md +1552 -0
- package/research/llm-summarization/prompt-engineering-2026.md +1426 -0
- package/research/llm-summarization/prototype-results.md +56 -0
- package/research/llm-summarization/provider-switching-patterns-2026.md +2153 -0
- package/research/llm-summarization/typescript-llm-libraries-2026.md +2436 -0
- package/research/mdcontext-error-analysis.md +521 -0
- package/research/mdcontext-pudding/00-EXECUTIVE-SUMMARY.md +282 -0
- package/research/mdcontext-pudding/01-index-embed.md +956 -0
- package/research/mdcontext-pudding/02-search-COMMANDS.md +142 -0
- package/research/mdcontext-pudding/02-search-SUMMARY.md +146 -0
- package/research/mdcontext-pudding/02-search.md +970 -0
- package/research/mdcontext-pudding/03-context.md +779 -0
- package/research/mdcontext-pudding/04-navigation-and-analytics.md +803 -0
- package/research/mdcontext-pudding/04-tree.md +704 -0
- package/research/mdcontext-pudding/05-config.md +1038 -0
- package/research/mdcontext-pudding/06-links-summary.txt +87 -0
- package/research/mdcontext-pudding/06-links.md +679 -0
- package/research/mdcontext-pudding/07-stats.md +693 -0
- package/research/mdcontext-pudding/BUG-FIX-PLAN.md +388 -0
- package/research/mdcontext-pudding/P0-BUG-VALIDATION.md +167 -0
- package/research/mdcontext-pudding/README.md +168 -0
- package/research/mdcontext-pudding/TESTING-SUMMARY.md +128 -0
- package/research/npm_publish/011-npm-workflow-research-agent2.md +792 -0
- package/research/npm_publish/012-npm-workflow-research-agent1.md +530 -0
- package/research/npm_publish/013-npm-workflow-research-agent3.md +722 -0
- package/research/npm_publish/014-npm-workflow-synthesis.md +556 -0
- package/research/npm_publish/031-npm-workflow-task-analysis.md +134 -0
- package/research/research-quality-review.md +834 -0
- package/research/semantic-search/002-research-embedding-models.md +490 -0
- package/research/semantic-search/003-research-rag-alternatives.md +523 -0
- package/research/semantic-search/004-research-vector-search.md +841 -0
- package/research/semantic-search/032-research-semantic-search.md +427 -0
- package/research/semantic-search/embedding-text-analysis.md +156 -0
- package/research/semantic-search/multi-word-failure-reproduction.md +171 -0
- package/research/semantic-search/query-processing-analysis.md +207 -0
- package/research/semantic-search/root-cause-and-solution.md +114 -0
- package/research/semantic-search/threshold-validation-report.md +69 -0
- package/research/semantic-search/vector-search-analysis.md +63 -0
- package/research/task-management-2026/00-synthesis-recommendations.md +295 -0
- package/research/task-management-2026/01-ai-workflow-tools.md +416 -0
- package/research/task-management-2026/02-agent-framework-patterns.md +476 -0
- package/research/task-management-2026/03-lightweight-file-based.md +567 -0
- package/research/task-management-2026/04-established-tools-ai-features.md +541 -0
- package/research/task-management-2026/linear/01-core-features-workflow.md +771 -0
- package/research/task-management-2026/linear/02-api-integrations.md +930 -0
- package/research/task-management-2026/linear/03-ai-features.md +368 -0
- package/research/task-management-2026/linear/04-pricing-setup.md +205 -0
- package/research/task-management-2026/linear/05-usage-patterns-best-practices.md +605 -0
- package/research/test-path-issues.md +276 -0
- package/review/ALP-76/1-error-type-design.md +962 -0
- package/review/ALP-76/2-error-handling-patterns.md +906 -0
- package/review/ALP-76/3-error-presentation.md +624 -0
- package/review/ALP-76/4-test-coverage.md +625 -0
- package/review/ALP-76/5-migration-completeness.md +440 -0
- package/review/ALP-76/6-effect-best-practices.md +755 -0
- package/scripts/apply-branch-protection.sh +47 -0
- package/scripts/branch-protection-templates.json +79 -0
- package/scripts/prototype-summarization.ts +346 -0
- package/scripts/rebuild-hnswlib.js +58 -0
- package/scripts/setup-branch-protection.sh +64 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/active-provider.json +7 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/bm25.json +541 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/bm25.meta.json +5 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/config.json +8 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/embeddings/openai_text-embedding-3-small_512/vectors.bin +0 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/embeddings/openai_text-embedding-3-small_512/vectors.meta.bin +0 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/indexes/documents.json +60 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/indexes/links.json +13 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/.mdcontext/indexes/sections.json +1197 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/configuration-management.md +99 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/distributed-systems.md +92 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/error-handling.md +78 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/failure-automation.md +55 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/job-context.md +69 -0
- package/src/__tests__/fixtures/semantic-search/multi-word-corpus/process-orchestration.md +99 -0
- package/src/cli/argv-preprocessor.test.ts +210 -0
- package/src/cli/argv-preprocessor.ts +202 -0
- package/src/cli/cli.test.ts +627 -0
- package/src/cli/commands/backlinks.ts +54 -0
- package/src/cli/commands/config-cmd.ts +642 -0
- package/src/cli/commands/context.ts +285 -0
- package/src/cli/commands/duplicates.ts +122 -0
- package/src/cli/commands/embeddings.ts +529 -0
- package/src/cli/commands/index-cmd.ts +480 -0
- package/src/cli/commands/index.ts +16 -0
- package/src/cli/commands/links.ts +52 -0
- package/src/cli/commands/search.ts +1281 -0
- package/src/cli/commands/stats.ts +149 -0
- package/src/cli/commands/tree.ts +128 -0
- package/src/cli/config-layer.ts +176 -0
- package/src/cli/error-handler.test.ts +235 -0
- package/src/cli/error-handler.ts +655 -0
- package/src/cli/flag-schemas.ts +341 -0
- package/src/cli/help.ts +588 -0
- package/src/cli/index.ts +9 -0
- package/src/cli/main.ts +435 -0
- package/src/cli/options.ts +41 -0
- package/src/cli/shared-error-handling.ts +199 -0
- package/src/cli/typo-suggester.test.ts +105 -0
- package/src/cli/typo-suggester.ts +130 -0
- package/src/cli/utils.ts +259 -0
- package/src/config/file-provider.test.ts +320 -0
- package/src/config/file-provider.ts +273 -0
- package/src/config/index.ts +72 -0
- package/src/config/integration.test.ts +667 -0
- package/src/config/precedence.test.ts +277 -0
- package/src/config/precedence.ts +451 -0
- package/src/config/schema.test.ts +414 -0
- package/src/config/schema.ts +603 -0
- package/src/config/service.test.ts +320 -0
- package/src/config/service.ts +243 -0
- package/src/config/testing.test.ts +264 -0
- package/src/config/testing.ts +110 -0
- package/src/core/index.ts +1 -0
- package/src/core/types.ts +113 -0
- package/src/duplicates/detector.test.ts +183 -0
- package/src/duplicates/detector.ts +414 -0
- package/src/duplicates/index.ts +18 -0
- package/src/embeddings/embedding-namespace.test.ts +300 -0
- package/src/embeddings/embedding-namespace.ts +947 -0
- package/src/embeddings/heading-boost.test.ts +222 -0
- package/src/embeddings/hnsw-build-options.test.ts +198 -0
- package/src/embeddings/hyde.test.ts +272 -0
- package/src/embeddings/hyde.ts +264 -0
- package/src/embeddings/index.ts +10 -0
- package/src/embeddings/openai-provider.ts +414 -0
- package/src/embeddings/pricing.json +22 -0
- package/src/embeddings/provider-constants.ts +204 -0
- package/src/embeddings/provider-errors.test.ts +967 -0
- package/src/embeddings/provider-errors.ts +565 -0
- package/src/embeddings/provider-factory.test.ts +240 -0
- package/src/embeddings/provider-factory.ts +225 -0
- package/src/embeddings/provider-integration.test.ts +788 -0
- package/src/embeddings/query-preprocessing.test.ts +187 -0
- package/src/embeddings/semantic-search-threshold.test.ts +508 -0
- package/src/embeddings/semantic-search.ts +1270 -0
- package/src/embeddings/types.ts +359 -0
- package/src/embeddings/vector-store.ts +708 -0
- package/src/embeddings/voyage-provider.ts +313 -0
- package/src/errors/errors.test.ts +845 -0
- package/src/errors/index.ts +533 -0
- package/src/index/ignore-patterns.test.ts +354 -0
- package/src/index/ignore-patterns.ts +305 -0
- package/src/index/index.ts +4 -0
- package/src/index/indexer.ts +684 -0
- package/src/index/storage.ts +260 -0
- package/src/index/types.ts +147 -0
- package/src/index/watcher.ts +189 -0
- package/src/index.ts +30 -0
- package/src/integration/search-keyword.test.ts +678 -0
- package/src/mcp/server.ts +612 -0
- package/src/parser/index.ts +1 -0
- package/src/parser/parser.test.ts +291 -0
- package/src/parser/parser.ts +394 -0
- package/src/parser/section-filter.test.ts +277 -0
- package/src/parser/section-filter.ts +392 -0
- package/src/search/__tests__/hybrid-search.test.ts +650 -0
- package/src/search/bm25-store.ts +366 -0
- package/src/search/cross-encoder.test.ts +253 -0
- package/src/search/cross-encoder.ts +406 -0
- package/src/search/fuzzy-search.test.ts +419 -0
- package/src/search/fuzzy-search.ts +273 -0
- package/src/search/hybrid-search.ts +448 -0
- package/src/search/path-matcher.test.ts +276 -0
- package/src/search/path-matcher.ts +33 -0
- package/src/search/query-parser.test.ts +260 -0
- package/src/search/query-parser.ts +319 -0
- package/src/search/searcher.test.ts +280 -0
- package/src/search/searcher.ts +724 -0
- package/src/search/wink-bm25.d.ts +30 -0
- package/src/summarization/cli-providers/claude.ts +202 -0
- package/src/summarization/cli-providers/detection.test.ts +273 -0
- package/src/summarization/cli-providers/detection.ts +118 -0
- package/src/summarization/cli-providers/index.ts +8 -0
- package/src/summarization/cost.test.ts +139 -0
- package/src/summarization/cost.ts +102 -0
- package/src/summarization/error-handler.test.ts +127 -0
- package/src/summarization/error-handler.ts +111 -0
- package/src/summarization/index.ts +102 -0
- package/src/summarization/pipeline.test.ts +498 -0
- package/src/summarization/pipeline.ts +231 -0
- package/src/summarization/prompts.test.ts +269 -0
- package/src/summarization/prompts.ts +133 -0
- package/src/summarization/provider-factory.test.ts +396 -0
- package/src/summarization/provider-factory.ts +178 -0
- package/src/summarization/types.ts +184 -0
- package/src/summarize/budget-bugs.test.ts +620 -0
- package/src/summarize/formatters.ts +419 -0
- package/src/summarize/index.ts +20 -0
- package/src/summarize/summarizer.test.ts +275 -0
- package/src/summarize/summarizer.ts +597 -0
- package/src/summarize/verify-bugs.test.ts +238 -0
- package/src/types/huggingface-transformers.d.ts +66 -0
- package/src/utils/index.ts +1 -0
- package/src/utils/tokens.test.ts +142 -0
- package/src/utils/tokens.ts +186 -0
- package/tests/fixtures/cli/.mdcontext/active-provider.json +7 -0
- package/tests/fixtures/cli/.mdcontext/config.json +8 -0
- package/tests/fixtures/cli/.mdcontext/embeddings/openai_text-embedding-3-small_512/vectors.bin +0 -0
- package/tests/fixtures/cli/.mdcontext/embeddings/openai_text-embedding-3-small_512/vectors.meta.bin +0 -0
- package/tests/fixtures/cli/.mdcontext/indexes/documents.json +33 -0
- package/tests/fixtures/cli/.mdcontext/indexes/links.json +12 -0
- package/tests/fixtures/cli/.mdcontext/indexes/sections.json +247 -0
- package/tests/fixtures/cli/README.md +9 -0
- package/tests/fixtures/cli/api-reference.md +11 -0
- package/tests/fixtures/cli/getting-started.md +11 -0
- package/tests/integration/embed-index.test.ts +712 -0
- package/tests/integration/search-context.test.ts +469 -0
- package/tests/integration/search-semantic.test.ts +522 -0
- package/tsconfig.json +26 -0
- package/vitest.config.ts +16 -0
- package/vitest.setup.ts +12 -0
|
@@ -0,0 +1,416 @@
|
|
|
1
|
+
# AI Workflow Task Management Tools - 2026 Research
|
|
2
|
+
|
|
3
|
+
**Research Date:** January 21, 2026
|
|
4
|
+
**Focus:** Modern alternatives to GitHub Projects/Issues for AI-generated task management
|
|
5
|
+
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
## Executive Summary
|
|
9
|
+
|
|
10
|
+
The landscape for managing AI-generated work items has evolved significantly in 2026. Traditional project management tools now embed AI deeply into their core features, while new AI-native platforms have emerged specifically for agent orchestration. Gartner predicts that 40% of enterprise applications will embed AI agents by the end of 2026, up from less than 5% in 2025.
|
|
11
|
+
|
|
12
|
+
The key shift: we've moved from tools that help humans track tasks to platforms where AI agents create, prioritize, and even execute work items autonomously.
|
|
13
|
+
|
|
14
|
+
---
|
|
15
|
+
|
|
16
|
+
## Tier 1: AI-Native & Agent-First Tools
|
|
17
|
+
|
|
18
|
+
### 1. Linear (with Linear for Agents)
|
|
19
|
+
|
|
20
|
+
**Description:** A fast, minimal, and opinionated project management tool built for software teams. Linear for Agents allows teams to delegate work to AI agents for code generation and technical tasks.
|
|
21
|
+
|
|
22
|
+
**AI Features:**
|
|
23
|
+
|
|
24
|
+
- Semantic search with AI-powered context understanding
|
|
25
|
+
- Connects to Cursor, Claude, ChatGPT, and other AI tools
|
|
26
|
+
- AI-assisted issue triaging, duplicate detection, and completion time prediction
|
|
27
|
+
- API designed for LLM integration to generate backlogs
|
|
28
|
+
|
|
29
|
+
**Pros:**
|
|
30
|
+
|
|
31
|
+
- Keyboard-first design perfect for developers
|
|
32
|
+
- Blazingly fast performance
|
|
33
|
+
- Excellent GitHub integration (PRs auto-update issue status)
|
|
34
|
+
- Growing ecosystem of AI agent integrations
|
|
35
|
+
- Clean, modern interface
|
|
36
|
+
|
|
37
|
+
**Cons:**
|
|
38
|
+
|
|
39
|
+
- Opinionated workflows may not fit all teams
|
|
40
|
+
- Paid plans required for larger teams
|
|
41
|
+
- "Increasing pressure to upgrade to enterprise, new features locked behind expensive plan"
|
|
42
|
+
|
|
43
|
+
**Pricing:**
|
|
44
|
+
|
|
45
|
+
- Free: Core features for small teams
|
|
46
|
+
- Standard: $8/user/month
|
|
47
|
+
- Plus: Custom pricing
|
|
48
|
+
- Enterprise: Custom pricing
|
|
49
|
+
|
|
50
|
+
**Best For:** Fast-moving tech startups, developer-first teams wanting AI integration
|
|
51
|
+
|
|
52
|
+
**Sources:** [Linear Official](https://linear.app), [Linear Review 2026](https://work-management.org/software-development/linear-review/), [ToolJunction Review](https://www.tooljunction.io/ai-tools/linear-app)
|
|
53
|
+
|
|
54
|
+
---
|
|
55
|
+
|
|
56
|
+
### 2. Taskade (Agent Sandbox)
|
|
57
|
+
|
|
58
|
+
**Description:** An AI-driven workspace that has evolved beyond task management into an "Agent Sandbox" where teams can build custom AI agents within project folders.
|
|
59
|
+
|
|
60
|
+
**AI Features:**
|
|
61
|
+
|
|
62
|
+
- Autonomous AI agents that handle tasks and research
|
|
63
|
+
- Custom agent creation (e.g., "Marketing Agent" that monitors tasks and generates content)
|
|
64
|
+
- Agents learn and adapt to evolving tasks
|
|
65
|
+
- AI-powered workflow automation across tools
|
|
66
|
+
|
|
67
|
+
**Pros:**
|
|
68
|
+
|
|
69
|
+
- Build custom AI agents within your workspace
|
|
70
|
+
- Real-time collaboration with chat and video conferencing
|
|
71
|
+
- Strong balance of capability and simplicity
|
|
72
|
+
- Affordable pricing with generous free tier
|
|
73
|
+
|
|
74
|
+
**Cons:**
|
|
75
|
+
|
|
76
|
+
- Limited reporting capabilities
|
|
77
|
+
- Weak permissions control
|
|
78
|
+
- Less deep project customization than competitors
|
|
79
|
+
|
|
80
|
+
**Pricing:**
|
|
81
|
+
|
|
82
|
+
- Free: $0/month - unlimited tasks, 250 AI generations/month
|
|
83
|
+
- Starter: $8/month - 1,000 AI generations, multiple workspaces
|
|
84
|
+
- Pro: $19/month - advanced features
|
|
85
|
+
- Enterprise: Custom
|
|
86
|
+
|
|
87
|
+
**Best For:** Remote teams, creative agencies, startups wanting custom AI agents
|
|
88
|
+
|
|
89
|
+
**Sources:** [Taskade AI Review 2026](https://thedigitalprojectmanager.com/tools/taskade-review/), [AI Chief Review](https://aichief.com/ai-business-tools/taskade-ai/)
|
|
90
|
+
|
|
91
|
+
---
|
|
92
|
+
|
|
93
|
+
### 3. Backlog.md
|
|
94
|
+
|
|
95
|
+
**Description:** A purpose-built tool for managing project collaboration between humans and AI agents in a git ecosystem. Uses "Spec-Driven AI Development" methodology.
|
|
96
|
+
|
|
97
|
+
**AI Features:**
|
|
98
|
+
|
|
99
|
+
- Task tracking across branches
|
|
100
|
+
- Status change callbacks for AI agents
|
|
101
|
+
- Integration with AI coding assistants
|
|
102
|
+
- Git-native workflow for AI-generated tasks
|
|
103
|
+
|
|
104
|
+
**Pros:**
|
|
105
|
+
|
|
106
|
+
- Designed specifically for AI-human collaboration
|
|
107
|
+
- Lives in your git repository (no external tool needed)
|
|
108
|
+
- Open source and transparent
|
|
109
|
+
- Perfect for AI coding assistant workflows
|
|
110
|
+
|
|
111
|
+
**Cons:**
|
|
112
|
+
|
|
113
|
+
- New tool (less mature ecosystem)
|
|
114
|
+
- Requires git-centric workflow
|
|
115
|
+
- Less visual/UI compared to traditional tools
|
|
116
|
+
|
|
117
|
+
**Pricing:** Free (Open Source)
|
|
118
|
+
|
|
119
|
+
**Best For:** Development teams using AI coding assistants extensively
|
|
120
|
+
|
|
121
|
+
**Sources:** [GitHub - Backlog.md](https://github.com/MrLesk/Backlog.md), [Voxxed Days 2026 Talk](https://m.devoxx.com/events/vdt26/talks/3798/backlog-md-the-simplest-project-management-tool-for-the-ai-era)
|
|
122
|
+
|
|
123
|
+
---
|
|
124
|
+
|
|
125
|
+
## Tier 2: Open Source AI-Ready Platforms
|
|
126
|
+
|
|
127
|
+
### 4. Plane.so (AI-Native Open Source)
|
|
128
|
+
|
|
129
|
+
**Description:** The #1 project management software on GitHub. Positions itself as an open-source Jira/Linear alternative with AI-native capabilities.
|
|
130
|
+
|
|
131
|
+
**AI Features:**
|
|
132
|
+
|
|
133
|
+
- AI-powered Pages for idea capture and note transformation
|
|
134
|
+
- Official MCP Server for AI assistant integration
|
|
135
|
+
- Enables AI to create, assign, and update tasks directly
|
|
136
|
+
- Use cases: AI Scrum Master, Automated Bug Triage, PRD to Project Plan
|
|
137
|
+
|
|
138
|
+
**Pros:**
|
|
139
|
+
|
|
140
|
+
- Self-hostable with 100% feature parity
|
|
141
|
+
- MCP integration for any AI client (not locked to one vendor)
|
|
142
|
+
- Generous free tier
|
|
143
|
+
- Strong community (GitHub-first)
|
|
144
|
+
- Great for compliance-focused industries
|
|
145
|
+
|
|
146
|
+
**Cons:**
|
|
147
|
+
|
|
148
|
+
- Less mature than commercial alternatives
|
|
149
|
+
- Community support vs. enterprise support
|
|
150
|
+
- AI features still evolving
|
|
151
|
+
|
|
152
|
+
**Pricing:**
|
|
153
|
+
|
|
154
|
+
- Community: Free (self-hosted)
|
|
155
|
+
- Free Cloud: Core features forever free
|
|
156
|
+
- Pro: Paid tier for advanced features
|
|
157
|
+
- Enterprise: Custom with self-hosted support
|
|
158
|
+
|
|
159
|
+
**Best For:** Teams wanting open-source + AI integration, government/regulated industries
|
|
160
|
+
|
|
161
|
+
**Sources:** [Plane.so](https://plane.so), [Plane MCP Server](https://skywork.ai/skypage/en/plane-mcp-server-ai-project-management/1979087899679039488), [GitHub](https://github.com/makeplane/plane)
|
|
162
|
+
|
|
163
|
+
---
|
|
164
|
+
|
|
165
|
+
### 5. Huly
|
|
166
|
+
|
|
167
|
+
**Description:** Open-source all-in-one replacement for Linear, Jira, Slack, and Notion. Known for remote collaboration features.
|
|
168
|
+
|
|
169
|
+
**AI Features:**
|
|
170
|
+
|
|
171
|
+
- Hulia AI assistant for automatic meeting transcription
|
|
172
|
+
- Upcoming MetaBrain: AI-generated meeting summaries, action item extraction
|
|
173
|
+
- CollectiveCortex: "Living memory" graph treating all content as retrievable context
|
|
174
|
+
- Lightweight autonomous AI coding agent (terminal-based, Rust)
|
|
175
|
+
|
|
176
|
+
**Pros:**
|
|
177
|
+
|
|
178
|
+
- Entirely self-hostable with zero license fees
|
|
179
|
+
- Virtual office spaces with audio/video conferencing
|
|
180
|
+
- Linear-inspired interface quality
|
|
181
|
+
- Ambitious AI roadmap
|
|
182
|
+
|
|
183
|
+
**Cons:**
|
|
184
|
+
|
|
185
|
+
- AI features still in development
|
|
186
|
+
- Smaller community than Plane
|
|
187
|
+
- Less established enterprise support
|
|
188
|
+
|
|
189
|
+
**Pricing:** Free (Open Source, self-hosted)
|
|
190
|
+
|
|
191
|
+
**Best For:** Remote teams, organizations wanting full control over their stack
|
|
192
|
+
|
|
193
|
+
**Sources:** [Huly.io](https://huly.io), [GitHub](https://github.com/hcengineering/platform), [Dupple Review](https://www.dupple.com/tools/hulyio)
|
|
194
|
+
|
|
195
|
+
---
|
|
196
|
+
|
|
197
|
+
## Tier 3: Enterprise Platforms with AI Enhancement
|
|
198
|
+
|
|
199
|
+
### 6. Notion (with Notion Agent)
|
|
200
|
+
|
|
201
|
+
**Description:** The popular workspace tool has evolved with AI Agents (launched September 2025) that provide autonomous data analysis and automated task management.
|
|
202
|
+
|
|
203
|
+
**AI Features:**
|
|
204
|
+
|
|
205
|
+
- Notion Agent: Takes on entire projects, breaks into tasks, assigns, drafts docs
|
|
206
|
+
- Can update/create hundreds of pages at once
|
|
207
|
+
- Converts notes to actionable to-do lists automatically
|
|
208
|
+
- Mobile AI transcription with summaries and action items
|
|
209
|
+
- Model selection (multiple AI providers)
|
|
210
|
+
|
|
211
|
+
**Pros:**
|
|
212
|
+
|
|
213
|
+
- Deeply integrated into existing Notion workflows
|
|
214
|
+
- Agent works in background while you continue other work
|
|
215
|
+
- Strong mobile experience
|
|
216
|
+
- Large ecosystem and community
|
|
217
|
+
|
|
218
|
+
**Cons:**
|
|
219
|
+
|
|
220
|
+
- Can become overwhelming for simple use cases
|
|
221
|
+
- AI add-on pricing on top of base subscription
|
|
222
|
+
- Performance can lag with large workspaces
|
|
223
|
+
|
|
224
|
+
**Pricing:**
|
|
225
|
+
|
|
226
|
+
- Free: Basic features
|
|
227
|
+
- Plus: $8/user/month
|
|
228
|
+
- Business: $15/user/month
|
|
229
|
+
- Enterprise: Custom
|
|
230
|
+
- AI Add-on: Additional cost per user
|
|
231
|
+
|
|
232
|
+
**Best For:** Teams already using Notion wanting AI automation
|
|
233
|
+
|
|
234
|
+
**Sources:** [Notion Releases](https://www.notion.com/releases), [Notion AI Review 2026](https://cybernews.com/ai-tools/notion-ai-review/), [Notion Agent Launch](https://mlq.ai/news/notion-launches-its-first-ai-agents-for-data-analysis-and-task-automation/)
|
|
235
|
+
|
|
236
|
+
---
|
|
237
|
+
|
|
238
|
+
### 7. ClickUp (with ClickUp Brain)
|
|
239
|
+
|
|
240
|
+
**Description:** All-in-one workspace with ClickUp Brain AI that connects tasks, docs, people, and integrates with external AI tools.
|
|
241
|
+
|
|
242
|
+
**AI Features:**
|
|
243
|
+
|
|
244
|
+
- Brain Max: Integrates other apps (Dropbox, SharePoint) for cross-stack responses
|
|
245
|
+
- Autopilot Agents: Generate daily/weekly reports, auto-generate task properties
|
|
246
|
+
- Custom agent creation with configurable behavior and actions
|
|
247
|
+
- MCP server connection for ChatGPT, Claude, Gemini
|
|
248
|
+
|
|
249
|
+
**Pros:**
|
|
250
|
+
|
|
251
|
+
- Comprehensive all-in-one platform
|
|
252
|
+
- Real-time dashboards pulling from tasks, docs, and chat
|
|
253
|
+
- Highly customizable workflows
|
|
254
|
+
- Strong external AI tool integration
|
|
255
|
+
|
|
256
|
+
**Cons:**
|
|
257
|
+
|
|
258
|
+
- Can be overwhelming (feature bloat)
|
|
259
|
+
- Steeper learning curve
|
|
260
|
+
- More expensive for full AI features
|
|
261
|
+
|
|
262
|
+
**Pricing:**
|
|
263
|
+
|
|
264
|
+
- Free: Limited features
|
|
265
|
+
- Unlimited: $7/user/month
|
|
266
|
+
- Business: $12/user/month
|
|
267
|
+
- Enterprise: Custom
|
|
268
|
+
- Brain Max: Additional AI tier
|
|
269
|
+
|
|
270
|
+
**Best For:** Large teams wanting everything in one place with AI
|
|
271
|
+
|
|
272
|
+
**Sources:** [ClickUp vs Jira 2026](https://clickup.com/blog/clickup-vs-jira/), [Zapier AI PM Tools](https://zapier.com/blog/best-ai-project-management-tools/)
|
|
273
|
+
|
|
274
|
+
---
|
|
275
|
+
|
|
276
|
+
### 8. Wrike (with Wrike Copilot)
|
|
277
|
+
|
|
278
|
+
**Description:** Enterprise project management with embedded AI chatbot and MCP server integration.
|
|
279
|
+
|
|
280
|
+
**AI Features:**
|
|
281
|
+
|
|
282
|
+
- Wrike Copilot: Full workspace access, risk analysis, detailed project explanations
|
|
283
|
+
- AI agents automate tasks based on prompts, triggers, and actions
|
|
284
|
+
- MCP server for ChatGPT, Claude, Gemini integration
|
|
285
|
+
- Project management data accessible from external AI apps
|
|
286
|
+
|
|
287
|
+
**Pros:**
|
|
288
|
+
|
|
289
|
+
- Enterprise-grade with AI integration
|
|
290
|
+
- Strong risk analysis capabilities
|
|
291
|
+
- Flexible AI tool connections
|
|
292
|
+
|
|
293
|
+
**Cons:**
|
|
294
|
+
|
|
295
|
+
- More complex/enterprise-focused
|
|
296
|
+
- Higher price point
|
|
297
|
+
- Overkill for small teams
|
|
298
|
+
|
|
299
|
+
**Best For:** Enterprises needing robust PM with AI analysis
|
|
300
|
+
|
|
301
|
+
**Sources:** [Zapier AI PM Tools 2026](https://zapier.com/blog/best-ai-project-management-tools/)
|
|
302
|
+
|
|
303
|
+
---
|
|
304
|
+
|
|
305
|
+
## Agent Orchestration Frameworks (For Custom Solutions)
|
|
306
|
+
|
|
307
|
+
If existing tools don't meet your needs, these frameworks enable building custom AI task management:
|
|
308
|
+
|
|
309
|
+
| Framework | Best For | Key Feature |
|
|
310
|
+
| ----------------------------- | ---------------------- | -------------------------------------- |
|
|
311
|
+
| **LangGraph** | Complex workflows | Graph-based, stateful orchestration |
|
|
312
|
+
| **CrewAI** | Collaborative agents | Role-playing agents, 32k+ GitHub stars |
|
|
313
|
+
| **AutoGen** | Microsoft ecosystem | Multi-agent conversation framework |
|
|
314
|
+
| **Microsoft Semantic Kernel** | Enterprise integration | Memory and goal planning |
|
|
315
|
+
|
|
316
|
+
**Sources:** [AI Multiple - Agentic Orchestration](https://research.aimultiple.com/agentic-orchestration/), [Shakudo - AI Agent Frameworks](https://www.shakudo.io/blog/top-9-ai-agent-frameworks)
|
|
317
|
+
|
|
318
|
+
---
|
|
319
|
+
|
|
320
|
+
## Comparison Matrix
|
|
321
|
+
|
|
322
|
+
| Tool | AI Agents | Self-Host | Open Source | Price/User | Best For |
|
|
323
|
+
| ---------- | ---------- | --------- | ----------- | ---------- | ---------------- |
|
|
324
|
+
| Linear | Yes | No | No | $8/mo | Dev teams |
|
|
325
|
+
| Taskade | Yes | No | No | $8/mo | Remote teams |
|
|
326
|
+
| Backlog.md | Yes | Yes | Yes | Free | Git workflows |
|
|
327
|
+
| Plane.so | Yes | Yes | Yes | Free | Compliance needs |
|
|
328
|
+
| Huly | Developing | Yes | Yes | Free | Remote collab |
|
|
329
|
+
| Notion | Yes | No | No | $8+/mo | Knowledge work |
|
|
330
|
+
| ClickUp | Yes | No | No | $7+/mo | All-in-one |
|
|
331
|
+
| Wrike | Yes | No | No | Enterprise | Large orgs |
|
|
332
|
+
|
|
333
|
+
---
|
|
334
|
+
|
|
335
|
+
## Key 2026 Trends
|
|
336
|
+
|
|
337
|
+
1. **MCP (Model Context Protocol) Integration**: Tools increasingly support MCP servers, allowing any AI assistant to interact with project management data.
|
|
338
|
+
|
|
339
|
+
2. **Agent-as-Team-Member**: AI agents are no longer just assistants; they're treated as team members that can own tasks, create subtasks, and report status.
|
|
340
|
+
|
|
341
|
+
3. **Spec-Driven AI Development**: Emerging methodology where specifications drive AI agent work, with tools like Backlog.md designed specifically for this pattern.
|
|
342
|
+
|
|
343
|
+
4. **Autonomous Project Management (APM)**: The manual update cycle is "officially dead" - AI monitors, updates, and manages backlogs automatically.
|
|
344
|
+
|
|
345
|
+
5. **Cross-Tool AI**: AI assistants aren't locked to one tool; they operate across your entire stack via MCP and API integrations.
|
|
346
|
+
|
|
347
|
+
---
|
|
348
|
+
|
|
349
|
+
## Recommendations
|
|
350
|
+
|
|
351
|
+
### For AI Coding Workflows (My Top Pick)
|
|
352
|
+
|
|
353
|
+
**Linear + Backlog.md combo**
|
|
354
|
+
|
|
355
|
+
- Use Linear for team-visible planning and roadmaps
|
|
356
|
+
- Use Backlog.md for git-native AI agent task handoffs
|
|
357
|
+
- Both integrate well with Claude, Cursor, and other AI coding tools
|
|
358
|
+
|
|
359
|
+
### For Maximum Flexibility (Open Source)
|
|
360
|
+
|
|
361
|
+
**Plane.so**
|
|
362
|
+
|
|
363
|
+
- Full MCP server support means any AI can integrate
|
|
364
|
+
- Self-hostable for compliance requirements
|
|
365
|
+
- Active development and strong community
|
|
366
|
+
|
|
367
|
+
### For Existing Tool Ecosystems
|
|
368
|
+
|
|
369
|
+
- **Notion users:** Notion Agent is surprisingly capable
|
|
370
|
+
- **Microsoft shops:** Microsoft Copilot + Claude integration
|
|
371
|
+
- **All-in-one needs:** ClickUp with Brain Max
|
|
372
|
+
|
|
373
|
+
### For Remote/Distributed Teams
|
|
374
|
+
|
|
375
|
+
**Huly** - Virtual office + project management + developing AI features
|
|
376
|
+
|
|
377
|
+
### For Custom Agent Workflows
|
|
378
|
+
|
|
379
|
+
Build on **LangGraph** or **CrewAI** with Linear/Plane as the task layer
|
|
380
|
+
|
|
381
|
+
---
|
|
382
|
+
|
|
383
|
+
## Conclusion
|
|
384
|
+
|
|
385
|
+
The biggest shift in 2026 is that AI agents are no longer just consumers of task data - they're active participants in task creation and management. The tools that best support this paradigm shift (Linear for Agents, Plane MCP, Taskade Agent Sandbox) are emerging as leaders for AI-first development teams.
|
|
386
|
+
|
|
387
|
+
For teams heavily using AI coding assistants like Claude Code, the git-native approach of Backlog.md combined with a visual tool like Linear or Plane provides the best balance of AI integration and human oversight.
|
|
388
|
+
|
|
389
|
+
---
|
|
390
|
+
|
|
391
|
+
## Sources
|
|
392
|
+
|
|
393
|
+
### Primary Tool References
|
|
394
|
+
|
|
395
|
+
- [Linear Official](https://linear.app)
|
|
396
|
+
- [Plane.so](https://plane.so)
|
|
397
|
+
- [Huly](https://huly.io)
|
|
398
|
+
- [Taskade](https://taskade.com)
|
|
399
|
+
- [Notion](https://notion.com)
|
|
400
|
+
- [ClickUp](https://clickup.com)
|
|
401
|
+
- [Backlog.md](https://github.com/MrLesk/Backlog.md)
|
|
402
|
+
|
|
403
|
+
### Research & Comparisons
|
|
404
|
+
|
|
405
|
+
- [Top 10+ Agentic Orchestration Frameworks 2026](https://research.aimultiple.com/agentic-orchestration/)
|
|
406
|
+
- [n8n AI Workflow Automation Tools 2026](https://blog.n8n.io/best-ai-workflow-automation-tools/)
|
|
407
|
+
- [Zapier Best AI Project Management Tools 2026](https://zapier.com/blog/best-ai-project-management-tools/)
|
|
408
|
+
- [Monday.com Linear Alternatives 2026](https://monday.com/blog/rnd/linear-alternatives/)
|
|
409
|
+
- [Digital PM Free AI Tools 2026](https://thedigitalprojectmanager.com/tools/free-ai-project-management-tools/)
|
|
410
|
+
- [Plane MCP Server Analysis](https://skywork.ai/skypage/en/plane-mcp-server-ai-project-management/1979087899679039488)
|
|
411
|
+
- [AI in Backlog Management Guide](https://thedigitalprojectmanager.com/productivity/ai-in-backlog-management/)
|
|
412
|
+
|
|
413
|
+
### AI Agent Market Data
|
|
414
|
+
|
|
415
|
+
- [Google Cloud AI Agent Trends 2026](https://cloud.google.com/resources/content/ai-agent-trends-2026)
|
|
416
|
+
- [Analytics Vidhya AI Agents Trends 2026](https://www.analyticsvidhya.com/blog/2026/01/ai-agents-trends/)
|